The United States Customs and Board Protection (CBP) uses AI to help screen cargo at ports of entry, validate identities as part of travel, and enhance awareness of threats at the border.
Below is an overview of each AI use case within CBP, as part of the Simplified DHS AI Use Case Inventory. More details about these use cases are available in the Full DHS AI Use Case Inventory on the DHS AI Use Case Inventory publication library.
AI use cases are listed by deployment status:
Pre-Deployment
Use Case Name: AI for Autonomous Situational Awareness
Use Case ID: DHS-P2
Use Case Summary: The AI for Autonomous Situational Awareness System is intended to use Internet of Things IoT sensor kits to covertly detect and track illicit cross-border traffic in remote locations. The system will leverage a motion image/video system enhanced with Artificial Intelligence that is capable of vehicle detection and direction determination. It will also incorporate a motion sensor that, when triggered, wakes up a high-resolution camera to capture a series of pictures, with additional sensors providing confirmation prior to camera capture. Images captured will be processed by Artificial Intelligence models to classify objects, determine vehicle direction at intersections, and provide imagery sufficient for re-identification. Ultimately, the system is intended to create a low footprint, low cost, low power system to provide situational awareness and covert detection., detection and identification of objects at or near the U.S. border, and possibly classification.
Use Case Topic Area: Law & Justice
Deployment Status: Pre-deployment (Initiation)
Safety- and/or rights-impacting? No, use case is too new to fully assess impacts; will be reassessed before end of initiation stage.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Vessel Detection
Use Case ID: DHS-38
Use Case Summary: Integrated technologies and analytics enhance maritime detection and the sensor network. Machine-assisted and AI-enhanced detection and tracking allow for improved illicit vessel detection in areas with high volumes of legitimate trade and recreational water vessel traffic by increasing situational awareness and responsiveness to threats. Vessel Detection allows an agent to set a search area with criteria (e.g., people, drones, vehicles) and transmit those criteria to the sensors. Images detected by the sensors are automatically recognized using Artificial Intelligence. The AI algorithms filter, detect, and recognize objects, dividing them into Items of Interest (IoI) and other objects. Detections of IoI are shared with other detection systems while detections of other objects (e.g., animals) are not shared. IoIs can be tracked and maintained across multiple sensors seamlessly.
Use Case Topic Area: Law & Justice
Deployment Status: Pre-deployment (Initiation)
Safety- and/or rights-impacting? No, use case is too new to fully assess impacts; will be reassessed before end of initiation stage.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Commodity Detection Model (Cargo Insights Team)
Use Case ID: DHS-69
Use Case Summary: This project leverages computer vision with object detection and a neural network to analyze X-Ray images and predict the commodity code of detected objects. It analyzes X-Ray images and predicts the commodity code of detected objects, reducing the need for users to manually enter codes for all commodities presented. The model provides a commodity code prediction label with bounding boxes on the image.
Use Case Topic Area: Law & Justice
Deployment Status: Pre-deployment (Initiation)
Safety- and/or rights-impacting? No, use case is too new to fully assess impacts; will be reassessed before end of initiation stage.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Trade Entity Risk Model (formerly Cargo Entity Risk Model)
Use Case ID: DHS-95
Use Case Summary: The project employs a collection of supervised machine learning models designed to assess the risk associated with trade entities. These models analyze various characteristics and profiles of trade entities to evaluate potential risks across different cargo enforcement domains. The Trade Entity Risk model enhances existing predictive threat models by compiling a risk profile that includes historical transaction data, relationships with trading partners, and relevant compliance information. This aggregated data helps create measurable risk indicators for trade entities. The calculated risk measures produced by the Trade Entity Risk model can be integrated into broader AI and machine learning systems to improve the evaluation of cargo-related threats. This output supports the standardization of trade entity risk, facilitating better data development for future predictive models. This approach aims to enhance the overall effectiveness of risk assessment in cargo management while maintaining a focus on data privacy and security.
Use Case Topic Area: Law & Justice
Deployment Status: Pre-deployment (Initiation)
Safety- and/or rights-impacting? No, use case is too new to fully assess impacts; will be reassessed before end of initiation stage.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Automated Data Annotation
Use Case ID: DHS-165
Use Case Summary: The Automated Data Annotation system simplifies and enhances data annotation for machine learning by providing tools to efficiently label datasets across various formats, such as images, text, and videos. It supports both manual labeling with an intuitive web interface and automated labeling powered by machine learning to accelerate the process. Human annotation is offered to verify and validate the automated annotations. The intended purpose of the AI is to generate domain specific training data to facilitate model training for specific mission use cases. The expected benefit is increased accuracy and confidence in model development and high-quality, labeled datasets in JavaScript Object Notation (JSON) format ready for machine learning. It also provides metadata, including annotation metrics and quality insights, to ensure accuracy and support model training workflows.
Use Case Topic Area: Mission-Enabling (internal agency support)
Deployment Status: Pre-deployment (Initiation)
Safety- and/or rights-impacting? No, use case is too new to fully assess impacts; will be reassessed before end of initiation stage.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Public Information Compilation for Travel Threat Analysis (Dataminr)
Use Case ID: DHS-183
Use Case Summary: CBP uses Dataminr, a commercially available open-source alerting tool, which compiles publicly available information to provide alerts for possible threats related to national security, border violence, CBP facilities, CBP employee safety, and other topics with a CBP-nexus involving air, sea, and land travel to and/or from the U.S. This tool significantly reduces the amount of time it takes for users to collect and compile this data. CBP manually enters parameters related to these topics into Dataminr. The results provide a summary of complied information, citation to information sources, and the possible threat (e.g., facility disruption, border violence, natural disaster, or terrorism). CBP employees review these results, including the source information, to further research the information to determine if there is a possible threat.
Use Case Topic Area: Mission-Enabling (internal agency support)
Deployment Status: Pre-deployment (Acquisition and/or Development)
Safety- and/or rights-impacting? No. It was presumed safety-impacting relating to detecting weapons or violence, but the DHS Chief AI Officer determined this use case does not satisfy the definition of safety-impacting AI in M-24-10. For this use case, the AI output is compiled publicly available information for awareness. No decisions or actions come directly from the information presented by Dataminr. CBP employees further research the information, including reading the source information, to determine if there is a possible threat and then create an appropriate response or notification based on that research. Read more about safety and/or rights-impacting AI.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: AI Enabled Autonomous Underwater Vehicle
Use Case ID: DHS-194
Use Case Summary: Advanced sonar, navigation, and communications system subsea vehicle is a fully integrated, hand-portable, low detection threshold system that has the small footprint and maneuverability to inspect underwater infrastructure. It integrates Doppler Velocity Log (DVL), Ultra-Short Baseline (USBL), Inertial Navigation System (INS), and acoustic and optical modems. This enables highly reliable, fully autonomous underwater missions and provides obstacle detection and collision avoidance. The system will be developed to assist in the detection of parasitic smuggling attempts on the outer hull of maritime vessels. Office of Field Operations (OFO) has identified significant potential for smuggling of narcotics attached to the outer hull of marine vessels entering and exiting ports of entry. The current identification method is using dive teams or borrowing larger Remotely Operated Vehicle (ROV) units from Local, State, or Federal partners. Through autonomous systems, OFO can more efficiently and safely identify anomalies/items of interest. The technology allows for increased shared situational awareness in real time for OFO and strategic partners and improves mission planning and agent and officer safety, while reducing reactionary gaps.
Use Case Topic Area: Law & Justice
Deployment Status: Pre-deployment (Initiation)
Safety- and/or rights-impacting? No, use case is too new to fully assess impacts; will be reassessed before end of initiation stage.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Relocatable Multi-Sensor System
Use Case ID: DHS-234
Use Case Summary: MDF correlates sensor data of different types into an integrated operational picture, allowing the user to see simplified, single entity tracks in highly complex scenarios. The system prioritizes items of interest (IOI) automatically based upon user intent and automatically cues sensors. MDF also classifies detections into groups it is trained for, including aircraft, humans, and vehicles. This does not include any nexus to biometric detection or image processing. The system uses advanced sensor technology to differentiate valid IOI, such as unmanned aircraft systems and humans, from other detections such as animals or environmental objects. By integrating radar and other sensor data, the system filters out false alarms, ensuring more accurate identification of potential IOI. This capability enhances CBP's ability to focus on legitimate risks while minimizing the time spent on non-threatening activities, improving operational efficiency at border and security checkpoints. The outputs include real-time data identifying and categorizing potential IOI while filtering out false or non-relevant IOI like animals. These outputs are used to provide situational awareness and support decision-making for CBP personnel.
Use Case Topic Area: Law & Justice
Deployment Status: Pre-deployment (Initiation)
Safety- and/or rights-impacting? No, use case is too new to fully assess impacts; will be reassessed before end of initiation stage.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Integrated Defense and Security Solutions (IDSS)
Use Case ID: DHS-311
Use Case Summary: CBP employs computed tomography x-ray systems with automated recognition technology for the inline screening of high-volume parcels to detect contraband. The system integrates AI-driven analytics into non-intrusive inspection systems, enhancing screening efficiency and accuracy by identifying anomalies for CBP personnel to review and, if necessary, conduct additional screening. The systems improve the screening efficiency and accuracy of contraband detection in international express consignment and mail inspection. The system provides a segmented image, highlighting anomalies for further inspection by CBP personnel.
Use Case Topic Area: Law & Justice
Deployment Status: Pre-deployment (Initiation)
Safety- and/or rights-impacting? No
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Advanced Analytics for X-ray Images (AAXI)
Use Case ID: DHS-313
Use Case Summary: Advanced Analytics for X-ray Images (AAXI) aims to address the problem of anomaly detection in empty commercial vehicles entering the U.S. at land border ports of entry. The AI models achieve this goal by encoding past x-ray images of vehicular border crossings in a semantically meaningful way and comparing the current crossing to detect differences amongst the images to identify anomalies. The system produces bounding boxes around an anomaly or unidentifiable object(s) within an image or any portion of the image that cannot be identified or explained. Benefits include enhancement of the capability of humans to consistently detect items of interest/concern present (and possibly concealed) in vehicles crossing into the United States, and increased clearance rate at border crossings so that vehicles operating safely and lawfully may pass through the border faster.
Use Case Topic Area: Law & Justice
Deployment Status: Pre-deployment (Acquisition and/or Development)
Safety- and/or rights-impacting? Yes. Rights-impacting. Before this AI use case is deployed, it will comply with risk management practices for deployed safety impacting AI. Read [LINK to FAQ] about compliance with required minimum risk management practices.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Advance RPM Maintenance Operating Reporter (ARMOR)
Use Case ID: DHS-314
Use Case Summary: Utilizing AI and physical modeling, the Advance Radiation Portal Monitor (RPM) Maintenance Operating Reporter (ARMOR) project provides predictive maintenance of RPMs, detecting issues with the equipment before the issue causes the screening lane to be inoperable. The system will provide a listing of malfunctioning RPMs categorized by issue severity and predicted date of failure, which will be used to create service tickets. ARMOR will shorten time to service/repair/maintenance of RPMs by two weeks. ARMOR will allow better distribution of resources (travel, spare parts, etc.) with a potential cost decrease of 25-50%. Through decreased outage time, and prediction of equipment degradation, ARMOR will increase radiological/nuclear (R/N) security on U.S. borders.
Use Case Topic Area: Mission-Enabling (internal agency support)
Deployment Status: Pre-deployment (Acquisition and/or Development)
Safety- and/or rights-impacting? Yes. Safety-impacting. Before this AI use case is deployed, it will comply with risk management practices for deployed safety impacting AI. Read [LINK to FAQ] about compliance with required minimum risk management practices.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: RAPTOR (Rapid Tactical Operations Reconnaissance)
Use Case ID: DHS-317
Use Case Summary: RAPTOR (Rapid Tactical Operations Reconnaissance) leverages Artificial Intelligence (AI) to enhance border security through real-time surveillance and reconnaissance. The AI system processes data from radar, infrared sensors, and video surveillance to detect and track suspicious activities along U.S. borders. By incorporating AI-powered vessel hull reading, RAPTOR significantly boosts domain awareness, enabling intelligence-driven operations for CBP-AMO marine interdiction agents. This technology enhances operational capabilities and officer safety during border security missions.
Use Case Topic Area: Law & Justice
Deployment Status: Pre-deployment (Initiation)
Safety- and/or rights-impacting? No, use case is too new to fully assess impacts; will be reassessed before end of initiation stage.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: AI to Generate Testable Synthetic Data
Use Case ID: DHS-2362
Use Case Summary: CBP’s Cargo Systems Program Directorate (CSPD) is exploring the use of Artificial Intelligence (AI) to generate synthetic data for trade partners. This AI-driven approach aims to create realistic test datasets that mirror actual trade data, enabling trade partners to effectively test new data formats and APIs within the Automated Commercial Environment (ACE). By leveraging AI-generated synthetic data, CSPD seeks to enhance testing accuracy, streamline development processes, and ensure smoother integration of new capabilities into ACE.
Use Case Topic Area: Mission-Enabling (internal agency support)
Deployment Status: Pre-deployment (Initiation)
Safety- and/or rights-impacting? No, use case is too new to fully assess impacts; will be reassessed before end of initiation stage.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Anomaly Detection COV Structure
Use Case ID: DHS-2363
Use Case Summary: CBP is seeking anomaly detection algorithm (ADA) models that can run on U.S. government systems for rapid screening of passenger and cargo vehicles. The desired end state is a suite of algorithms that supports CBP's non-intrusive inspection (NII) image analysis for detecting anomalies and interdicting contraband to assist CBP officers’ image review with specific interest on algorithms that facilitate screening for contraband and anomaly detection in passenger vehicles and cargo conveyances. This solution will assist CBP officers in adjudicating large-scale NII x-ray images. The solution will identify regions of interest within the structure of commercially owned vehicles (COVs) and detect anomalies within these regions. It will place bounding boxes around an anomaly or unidentifiable object(s) within an image or any portion of the image that cannot be identified or explained. The algorithm will support the review and analysis conducted by image analysts during NII x-ray image adjudication, ultimately reducing overall review time for NII images. It is expected that this will enhance the capability of humans to consistently detect items of interest/concern present (and possibly concealed) in vehicles crossing into the United States and increase clearance rate at border crossings, so that vehicles operating safely and lawfully may pass through the border faster.
Use Case Topic Area: Law & Justice
Deployment Status: Pre-deployment (Initiation)
Safety- and/or rights-impacting? No, use case is too new to fully assess impacts; will be reassessed before end of initiation stage.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Anomaly Detection Homogenous Cargo
Use Case ID: DHS-2364
Use Case Summary: CBP is seeking anomaly detection algorithm (ADA) models that can run on U.S. government systems for rapid screening of passenger and cargo vehicles. The desired end state is a suite of algorithms that supports CBP's non-intrusive inspection (NII) image analysis for detecting anomalies and interdicting contraband to assist CBP officers’ image review with specific interest on algorithms that facilitate screening for contraband and anomaly detection in passenger vehicles and cargo conveyances. This solution will assist CBP officers in adjudicating large scale NII x-ray images. The solution will identify anomalies within homogenous cargo contained in commercially owned vehicles (COVs). Bounding boxes around an anomaly or unidentifiable object(s) within an image or any portion of the image that cannot be identified or explained. The algorithm will support the review and analysis conducted by CBP image analysts during NII x-ray image adjudication ultimately reducing overall review time for NII images. It is expected that this will enhance the capability of humans to consistently detect items of interest/concern present (and possibly concealed) in vehicles crossing into the United States and increase clearance rate at border crossings, so that vehicles operating safely and lawfully may pass through the border faster.
Use Case Topic Area: Law & Justice
Deployment Status: Pre-deployment (Initiation)
Safety- and/or rights-impacting? No, use case is too new to fully assess impacts; will be reassessed before end of initiation stage.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Anomaly Detection POV Structure
Use Case ID: DHS-2365
Use Case Summary: CBP is seeking anomaly detection algorithm (ADA) models for rapid screening of passenger and cargo vehicles. The desired end state is a suite of algorithms that supports CBP's non-intrusive inspection (NII) image analysis for detecting anomalies and interdicting contraband to assist CBP officers’ image review with specific interest on algorithms that facilitate screening for contraband and anomaly detection in passenger vehicles and cargo conveyances. This solution will assist CBP officers in adjudicating large-scale NII x-ray images. The solution will identify regions of interest within the structure of privately owned vehicles (POVs) and detect anomalies within these regions. Bounding boxes around an anomaly or unidentifiable object(s) within an image or any portion of the image that cannot be identified or explained. The algorithm will support the review and analysis conducted by image analysts during NII x-ray image adjudication ultimately reducing overall review time for NII images while facilitating legitimate trade and travel. It is expected that this will enhance the capability of humans to consistently detect items of interest/concern present (and possibly concealed) in vehicles crossing into the United States and increase clearance rate at border crossings, so that vehicles operating safely and lawfully may pass through the border faster.
Use Case Topic Area: Law & Justice
Deployment Status: Pre-deployment (Initiation)
Safety- and/or rights-impacting? No, use case is too new to fully assess impacts; will be reassessed before end of initiation stage.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: CBP Careers Bot - Leo
Use Case ID: DHS-2366
Use Case Summary: Visitors to careers.cbp.gov can engage with a decision-tree based chat bot to help access CBP career related information and drive users to take the next action such as contacting a recruiter, attending a career event, or apply for a CBP Career. This bot will be enhanced over the next year to include responses driven by natural language processing (NLP) for predetermined intents.
Use Case Topic Area: Government Services (includes Benefits and Service Delivery)
Deployment Status: Pre-deployment (Initiation)
Safety- and/or rights-impacting? No, use case is too new to fully assess impacts; will be reassessed before end of initiation stage.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Computer Vision for Aerial Detection of Land and Open Water Items of Interest
Use Case ID: DHS-2367
Use Case Summary: CBP utilizes Computer Vision Machine Learning (CV/ML) models to automate the detection, classification, and tracking of potential cross-border air and ground threats. These AI-driven models process data from 360-degree, high-fidelity surveillance cameras mounted on stationary towers, enhancing the efficiency of border surveillance. By automating threat identification and tracking, the system reduces reliance on manual monitoring, providing real-time alerts and actionable insights to operators through an intuitive user interface.
Use Case Topic Area: Law & Justice
Deployment Status: Pre-deployment (Initiation)
Safety- and/or rights-impacting? No, use case is too new to fully assess impacts; will be reassessed before end of initiation stage.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: AI for Software Delivery
Use Case ID: DHS-2369
Use Case Summary: The Automated Commercial Environment (ACE) is the system through which the trade community reports imports and exports, and the government determines admissibility. This system is developed and maintained by the Cargo Systems Program Directorate (CSPD) within the Office of Information Technology (OIT) in Customs and Border Protection (CBP). ACE is a large system consisting of hundreds of applications with new capabilities added regularly. CSPD is seeking to incorporate AI into the software delivery process to reduce delivery time as well as increase the quality and security of the ACE system. The initial use case is to integrate AI into the development process to assist developers with code reviews so that when a request to modify code in a baseline is made by a developer AI is integrated into the continuous integration pipeline to examine the code for potential problems and inefficiencies. The AI model will identify coding errors and recommend fixes as well as make recommendations for improvement and optimization which the request reviewer will assess and determine what, if any, changes need to be made before the code is approved to go into the baseline. By reducing code review time and identifying potential issues earlier in the development CSPD expects to reduce the time to deliver changes and increase initial software quality.
Use Case Topic Area: Mission-Enabling (internal agency support)
Deployment Status: Pre-deployment (Initiation)
Safety- and/or rights-impacting? No, use case is too new to fully assess impacts; will be reassessed before end of initiation stage.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Optical Counter - UAS Detection
Use Case ID: DHS-2371
Use Case Summary: Current detection, classification [determining intention and/or threat level of each detection], and tracking of potential, cross-border air & ground threats mostly relies on human operators scanning the border environment with surveillance camera systems. This capability leverages 360 degree rotating, high fidelity cameras on stationary towers along with Computer Vision Machine Learning (CV/ML) models to automate the detection, classification, and tracking of potential cross-border air & ground incursions. This capability will automate cross-border air & ground item of interest detection, classification and tracking, enabling more efficient border surveillance and will provide alerts and tracks of detected/classified air & ground threats to system operators on a workstation user interface.
Use Case Topic Area: Law & Justice
Deployment Status: Pre-deployment (Initiation)
Safety- and/or rights-impacting? No, use case is too new to fully assess impacts; will be reassessed before end of initiation stage.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Thermal Power Generation with Geoseismic IoI Detection and Classification
Use Case ID: DHS-2375
Use Case Summary: The Thermal Power Generation and Geoseismic Item of Interest (IoI) detection and classification is able to convert surface heat fluctuations into electrical energy in order to power a seismic sensor. The data generated from the seismic sensor is then paired with a machine learning (ML) algorithm which is able to identify and classify Items of Interest (IoIs), noting the confidence interval that the detected seismic activity is correctly classified. Once an IoI is identified, users will receive alert notifications within their systems and determine the appropriate response in that area. Increases situational awareness in austere environments and reduces need for battery replacement since the devices are self-charging..
Use Case Topic Area: Law & Justice
Deployment Status: Pre-deployment (Initiation)
Safety- and/or rights-impacting? No, use case is too new to fully assess impacts; will be reassessed before end of initiation stage.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Underwater ROV
Use Case ID: DHS-2377
Use Case Summary: The Underwater Remotely Operated Vehicle (ROV) is a submersible drone capable of conducting inspections of maritime vessel hulls to detect underwater threats and contraband. The systems utilize supervised machine learning (ML) to assist in the identification of items of interest on a maritime ship’s hull. Outputs from the system will be the identification of threats and contraband. Users will use the output, an informed decision on if a potential threat or contraband is present on a hull, to determine if additional actions are required, The expected benefit of the system is that users will be able to identify potential threats and contraband on maritime vessels quickly. This identification will allow for the streamlined investigations of a ship’s hull without the need for a dive team.
Use Case Topic Area: Law & Justice
Deployment Status: Pre-deployment (Initiation)
Safety- and/or rights-impacting? No, use case is too new to fully assess impacts; will be reassessed before end of initiation stage.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Wellness and Physical Fitness Application
Use Case ID: DHS-2378
Use Case Summary: The use case helps service members build strength and durability by delivering structured, personalized workout plans to perform at their highest level. Coaches and users can start from a periodized base program built by Tactical Strength and Conditioning (TSAC) certified strength and conditioning specialists to optimize operational readiness — then customize it as much (or as little) as needed. The system will produce personalized physical fitness assessments and programs with real-time AI fitness monitoring and program adjustments, including metrics, graphs, and a display for group and/or individual trends analyses. This will increase user awareness of physical status and associated remedial actions, if necessary, with the ultimate goal of mitigating human capital costs through health and wellness awareness.
Use Case Topic Area: Health & Medical
Deployment Status: Pre-deployment (Initiation)
Safety- and/or rights-impacting? No, use case is too new to fully assess impacts; will be reassessed before end of initiation stage.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: API Security Vulnerability Technology
Use Case ID: DHS-2444
Use Case Summary: CBP plans to leverage Machine Learning (ML) and Natural Language Processing (NLP) to enhance API security testing and monitoring. These AI technologies will enable automated scanning and continuous monitoring of APIs to identify risks such as unauthorized access, data leaks, and misconfiguration. ML algorithms will analyze test results to generate comprehensive vulnerability reports, assign risk scores to prioritize critical issues, and offer step-by-step remediation guidance. Additionally, AI-driven continuous monitoring will provide real-time alerts for emerging vulnerabilities, ensuring robust API security throughout the development and deployment lifecycle.
Use Case Topic Area: Mission-Enabling (internal agency support)
Deployment Status: Pre-deployment (Initiation)
Safety- and/or rights-impacting? No, use case is too new to fully assess impacts; will be reassessed before end of initiation stage.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Cyber Threat Detection
Use Case ID: DHS-2446
Use Case Summary: Cyber Threat Detection is a cyber platform that enables CBP to detect, engage, and respond to malicious activity across hybrid cloud deployments, protecting both IT and networks. It uses generative AI (GenAI) to create decoys, lures, baits, and breadcrumbs, to detect threats and allows for more proactive threat identification and associated mitigation. The technology will establish a decoy file sharing capability such as SharePoint, Shared Drive, etc. with tailored decoy products or reports and monitor and alert on the access and interactions with the decoys. The technology enables the accurate detection of malicious activity in the cyber environment for actionable insights so that leadership can identify threats and efficiently mitigate them while reducing the cost of other security defenses. With the technology, the user will be alerted of detected compromise, evaluation of the creation of decoys, and the monitoring/analysis of interaction with the decoys from the adversary.
Use Case Topic Area: Mission-Enabling (internal agency support)
Deployment Status: Pre-deployment (Initiation)
Safety- and/or rights-impacting? No, use case is too new to fully assess impacts; will be reassessed before end of initiation stage.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Multi-media Insight Tool
Use Case ID: DHS-2449
Use Case Summary: The capability will leverage multimodal AI models and a cloud-native application programing interface (API) platform to find similar videos, or to search within videos for objects, spoken language, or sounds through recognition. The platform will provide users the ability to more efficiently search within videos for objects, spoken language, or sounds and the ability to rapidly ingest and extract insights for visual and audio data. With the technology, CBP will be able to more easily track and search for individuals, things, events (such as activated lights/sirens) in video, expanding to searching for an entity or event from one video file across multiple. The technology will integrate multimedia (audio and video) from multiple sources and sensors to generate by-source timelines and provide geospatial reference. With the extracted insights from visual and audio data, users will be able to detect simultaneous events across multiple video files and identify common key events where event times are known, inferring timestamps in linked or subsequent videos. Ultimately, the technology will allow for more efficient investigations.
Use Case Topic Area: Mission-Enabling (internal agency support)
Deployment Status: Pre-deployment (Initiation)
Safety- and/or rights-impacting? No, use case is too new to fully assess impacts; will be reassessed before end of initiation stage.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Position Description Generation and Evaluation
Use Case ID: DHS-2451
Use Case Summary: Incorporation of large langue models (LLMs) into the position description (PD) classification process, will enable accurate, speedy classification services delivery, increase uniformity in the classification process, and enable more robust PD language, leading to a more accurate assessment and ultimately a better applicant pool and candidate. Accurate PDs will also reduce the risk of PD based litigation or grievance against the agency. The system- created accurate PDs will be verified by Human Resources Specialist while reducing the administrative burden, allowing the agency to accomplish more with less staff.
Use Case Topic Area: Mission-Enabling (internal agency support)
Deployment Status: Pre-deployment (Initiation)
Safety- and/or rights-impacting? No, use case is too new to fully assess impacts; will be reassessed before end of initiation stage.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Source Code Development Tool
Use Case ID: DHS-2452
Use Case Summary: Current software development usually requires many hours of human coding labor. This capability accelerates software development by providing a generative artificial intelligence coding assistant. The coding assistant is based on large language models (LLM) and coding foundation models. End users may prompt the assistant to code, refine and complete a software project through natural language commands and queries. This capability will enable end users to develop software faster and more efficiently through the use of a generative artificial intelligence (GenAI) coding assistant and which will create functional software code for end users.
Use Case Topic Area: Mission-Enabling (internal agency support)
Deployment Status: Pre-deployment (Initiation)
Safety- and/or rights-impacting? No, use case is too new to fully assess impacts; will be reassessed before end of initiation stage.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Entity Resolution
Use Case ID: DHS-24
Use Case Summary: CBP leverages Artificial Intelligence (AI) to aggregate and analyze global trade data across multiple languages, enabling comprehensive network analysis to assess trade flows and associated risks. AI Machine Learning (ML) models streamline data collection, structuring, entity resolution, network analysis, and risk assessment, contributing to a dynamic knowledge graph and user-friendly interface for CBP personnel. This AI-driven approach enhances CBP’s ability to validate existing information, uncover complex trade networks, and provide actionable insights for cross-border investigations, ultimately supporting trade enforcement and economic security efforts.
Use Case Topic Area: Law & Justice
Deployment Status: Deployed (Operation and Maintenance)
Safety- and/or rights-impacting? No. It was presumed safety-impacting relating to trade and export enforcement actions and rights-impacting relating to law enforcement in certain contexts, but the DHS Chief AI Officer determined this use case does not satisfy the definition of either safety-impacting AI or rights-impacting AI in M-24-10. This use case assists by consolidating information from disparate data sources. The AI output is compiled information. Without the use of AI, it is likely the user would experience higher degrees of difficulty searching through multitudes of data elements. The illustration is then used by the analysts to determine high risk areas for trade targeting in the forced labor mission set. No decisions or actions come directly from the information presented by Altana. CBP employees further research the information, including reading the source information, alongside CBP data holdings to continue researching the probable supply chain before making any recommendations or taking any actions. Read more about safety and/or rights-impacting AI.
Face Recognition/Face Capture (FR/FC)? No.
Use Case Name: Autonomous Surveillance Tower (AST)
Use Case ID: DHS-35
Use Case Summary: The ASTs are lawfully deployed technologies used to support the U.S. Border Patrol mission between Ports of Entry. ASTs alert when detecting the presence of an IoI that the AI model was trained to detect (i.e., persons, vehicles, animals) in the image frame. When an IoI is detected in monitored areas, the information is sent as a notification to the user interface which generates an audible alert, a pop-up, and highlights the IoI in a green rectangle on the picture or video. A trained CBP agent or user, reviews the image to identify and classify the activity taking place. The AI merely alerts to the presence of an item it was trained to detect.
Use Case Topic Area: Law & Justice
Deployment Status: Deployed (Operation and Maintenance)
Safety- and/or rights-impacting? No. It was presumed rights-impacting relating to law enforcement in certain contexts, but the DHS Chief AI Officer determined this use case does not satisfy the definition of rights-impacting AI in M-24-10. The AI in this use case provides alerts when it detects the presence of an IoI (i.e., persons, vehicles, animals) in the image frame. With regard to persons, this computer vision application is trained to determine if the object in the image frame is a person with a certain of level of confidence and not another object that may be shaped similarly to a person. After the alert of a detection, a trained agent or user, reviews the image to identify and classify the activity taking place. The AI merely alerts to the presence of an item it was trained to detect. This is not a biometric system and does not identify or track specific individuals. Read more about safety and/or rights-impacting AI.
Face Recognition/Face Capture (FR/FC)? No.
Use Case Name: Automated Item of Interest Detection
Use Case ID: DHS-37
Use Case Summary: CBP uses software to analyze field imaging in monitored areas and to provide alerts when it detects the presence of an Item of Interest (IoI) that the AI model was trained to detect (i.e., persons, vehicles, animals) in the image frame. The software outputs include a superimposed outline surrounding of the IoI within the image or live feed. Each outline is color-coded based on the degree of certainty that the detection is the item it was trained to detect. The software allows the user to filter based on preferences for detections of IoI. This filtering allows for quick and efficient review and adjudication of the detection(s). After the alert of a detection, a trained CBP agent or user, reviews the image to identify and classify the activity taking place.
Use Case Topic Area: Law & Justice
Deployment Status: Deployed (Operation and Maintenance)
Safety- and/or rights-impacting? No. It was presumed rights-impacting relating to law enforcement in certain contexts, but the DHS Chief AI Officer determined this use case does not satisfy the definition of rights-impacting AI in M-24-10. The AI in this use case runs on video and images captured from lawfully deployed technologies used to support the U.S. Border Patrol mission between Ports of Entry. The AI provides alerts when it detects the presence of an IoI, such as persons, vehicles, animals in the image frame. With regard to persons, this computer vision application is trained to determine if the object in the image frame is a person with a certain of level of confidence and not another object that may be shaped similarly to a person. After the alert of a detection, a trained agent or user, reviews the image to identify and classify the activity taking place. The AI merely alerts to the presence of an item it was trained to detect. Read more about safety and/or rights-impacting AI.
Face Recognition/Face Capture (FR/FC)? No.
Use Case Name: Aircraft Landing Location Predictor (KESTREL)
Use Case ID: DHS-65
Use Case Summary: CBP uses Kestrel in CBP’s Air & Marine Operations Surveillance System (AMOSS) to aid in predicting where an aircraft will likely land based on historical flight paths. After an aircraft radar track has been declared suspect by the officer evaluating the track of interest through other research, Kestrel employs AI/ML to predict where the aircraft is most likely to land. The output results in a display of the top three final locations as displayed on AMOSS using green, yellow, and red lines to depict most to least probable outcomes.
Use Case Topic Area: Transportation
Deployment Status: Deployed (Operation and Maintenance)
Safety- and/or rights-impacting? No. It was presumed rights-impacting relating to law enforcement in certain contexts, but the DHS Chief AI Officer determined this use case does not satisfy the definition of rights-impacting AI in M-24-10. The AI outputs in this use case are used to predict aircraft landing locations and only after the suspect aircraft has already been identified based on the aircraft’s radar track. The output results in a display of the top three final locations using green, yellow, and red lines to depict most to least probable outcomes. These probable outcomes are continually updated and refreshed with up-to-date information and is used for potential contact and reporting purposes after a suspect aircraft has been identified. Read more about safety and/or rights-impacting AI.
Face Recognition/Face Capture (FR/FC)? No.
Use Case Name: Empty Container Detection Model (Cargo Insights Team)
Use Case ID: DHS-68
Use Case Summary: CBP's Empty Container Detection Model uses machine learning to identify and track empty containers in cargo shipments. By analyzing shipping data and container movements, the model helps detect potential discrepancies, such as empty containers being incorrectly labeled as full, improving the accuracy and efficiency of cargo management and inspections. This enhances border security and optimizes resource allocation for inspections. The model is designed to accurately identify and track empty containers in cargo shipments, preventing errors and fraud in cargo declarations. The AI improves accuracy, enhances efficiency by prioritizing legitimate containers for inspection, and strengthens security by detecting potential smuggling risks. The system applies a prediction label alongside a bounding box on record. Officers use this information along with all information provided to determine what, if any, further steps are required.
Use Case Topic Area: Law & Justice
Deployment Status: Operation and Maintenance
Safety- and/or rights-impacting? No
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Traveler Entity Resolution (formerly Passenger Targeting and Vetting)
Use Case ID: DHS-80
Use Case Summary: The Traveler Entity Resolution Model is designed to enhance the process of identity verification for travelers. It utilizes traveler data to identify individuals who may need additional review prior to travel. By analyzing various aspects of passenger information, the model helps prioritize individuals for further inspection, ensuring that resources are allocated effectively. This approach aims to improve both security and operational efficiency by focusing on individuals who may present higher risks. The model's outputs are integrated into existing systems, which assist personnel in making informed decisions regarding traveler screening. Importantly, human judgment remains central to the process, as personnel retain the final authority in all decision-making related to border security operations. Overall, this model supports a streamlined vetting process while maintaining a commitment to security and resource optimization.
Use Case Topic Area: Law & Justice
Deployment Status: Operation and Maintenance
Safety- and/or rights-impacting? Yes. Rights-impacting
Key Identified Risks & Mitigations: This AI system has been tested in operational or real-world environments and risks have been identified and mitigated. Information about risks and mitigations for this use case may be law enforcement sensitive; DHS continues to review details for potential future disclosure in accordance with applicable law and policy.
Read more about safety and/or rights-impacting AI and compliance with required minimum risk management practices.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Passport Anomaly Model (formerly Passport Anomaly Model (ODIN ESTA))
Use Case ID: DHS-81
Use Case Summary: The Passport Anomaly Model serves as a valuable tool for officers to analyze passport information and identify potential discrepancies. Given that there is no formal requirement to inform the U.S. when a new passport series is issued or an old series expires, Passport Anomaly Model helps officers assess passport validity based on historical trends. When a passport is submitted for analysis, Passport Anomaly Model provides an evaluation that indicates whether the passport displays typical or atypical characteristics. This assessment alerts officers to the possibility that a passport may need further examination, which could involve additional research to determine its authenticity or status. The use of Passport Anomaly Model enhances the ability of officers to ensure the integrity of travel documents while maintaining a focus on security and thoroughness in the review process.
Use Case Topic Area: Law & Justice
Deployment Status: Deployed (Operation and Maintenance)
Safety- and/or rights-impacting? No. It was presumed rights-impacting relating to risk assessments regarding immigration, but the DHS Chief AI Officer determined this use case does not satisfy the definition of rights-impacting AI in M-24-10. In this use case, the AI output is an assessment of passport validity in response to an officer's request for passport validation. This result could be related to an inconsistency or abnormality in a passport's pattern. This is a tool available to CBP officers for confirming the validity of a passport. This result is used to notify the CBP officer that a passport may require review, as it may be part of a newly released sequence, may be invalid, or even possibly fraudulent. This is only one piece of information provided to CBP Officers during the normal course of their duties. The officers would use any results provided to research the validity of the passport through other sources. Read more about safety and/or rights-impacting AI.
Face Recognition/Face Capture (FR/FC)? No.
Use Case Name: Agriculture Commodity Model (AGC)
Use Case ID: DHS-86
Use Case Summary: Agriculture Programs and Trade Liaisons (APTL) use AGC to leverage statistical sampling and supervised AI/ML models for risk-based inspection of selected agricultural commodities. The AGC Model maximizes CBP’s limited resources by prioritizing inspection of containers deemed high-risk. The AI output is a predicted risk result level for cargo shipments to identify agricultural pest risk. The predicted risk is integrated into the Automated Targeting System (ATS) - Import Cargo and utilized in APTL’s targeting workflow for agriculture pest risk analysis. If a cargo shipment is identified as high-risk for pest infestation, it is prioritized for inspection.
Use Case Topic Area: Law & Justice
Deployment Status: Deployed (Operation and Maintenance)
Safety- and/or rights-impacting? No. It was presumed safety-impacting relating to trade and export enforcement actions, but the DHS Chief AI Officer determined this use case does not satisfy the definition of safety-impacting AI in M-24-10. This use case’s AI output simply provides aggregated information to assist the user in locating relevant information to a research query. The operator reviews the aggregated information provided on the associated dashboards and determines any next steps. The AI output may be used to produce insights into the overall trade environment, but the output itself is supporting information for CBP personnel and their individual expertise and areas of responsibilities. It does not identify or track individuals. Read more about safety and/or rights-impacting AI.
Face Recognition/Face Capture (FR/FC)? No.
Use Case Name: Cargo Classification Tool (formerly HTS Classifier)
Use Case ID: DHS-94
Use Case Summary: CBP’s Cargo Classification Tool is a system that utilizes advanced text analysis techniques to evaluate product descriptions and suggest appropriate Harmonized Tariff Schedule codes. This tool enhances the efficiency of cargo evaluations by streamlining the classification of goods, which helps reduce errors and improve compliance. The Cargo Classification Tool supports trade compliance and cargo risk assessment by categorizing products based on their descriptions and attributes. This process aids in identifying potential risks associated with specific cargo types and past violations. The outputs generated by the Cargo Classification Tool provide a mapping of cargo descriptions to likely tariff codes, which enhances the accuracy of classifications. These outputs are designed to integrate smoothly into broader risk assessment frameworks, contributing to more effective targeting and evaluation of cargo security threats. Overall, the Cargo Classification Tool plays a crucial role in improving the accuracy and speed of cargo classification processes.
Use Case Topic Area: Law & Justice
Deployment Status: Operation and Maintenance
Safety- and/or rights-impacting? No
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Advanced Trade Analytics Program (ATAP)
Use Case ID: DHS-101
Use Case Summary: ATAP uses data analytics, machine learning, and AI to aggregate and analyze vast amounts of historical trade data and current activity data to identify patterns and trends in the trade environment that allow for greater data-driven insights into the threats and opportunities in CBP’s trade mission execution. The output of ATAP’s various analysis is typically provided through data visualizations and dashboards, allowing CBP personnel to examine the information as part of detecting and deterring non-compliance throughout the trade environment. CBP personnel use ATAP to aggregate information, visualize and display activity and patterns, and to assist the user in locating relevant information to a research query.
Use Case Topic Area: Diplomacy & Trade
Deployment Status: Deployed (Operation and Maintenance)
Safety- and/or rights-impacting? No. It was presumed safety-impacting relating to trade and export enforcement actions, but the DHS Chief AI Officer determined this use case does not satisfy the definition of safety-impacting AI in M-24-10. This use case’s AI output simply provides aggregated information to assist the user in locating relevant information to a research query. The operator reviews the aggregated information provided on the associated dashboards and determines any next steps. The AI output may be used to produce insights into the overall trade environment, but the output itself is supporting information for CBP personnel and their individual expertise and areas of responsibilities. It does not identify or track individuals. Read more about safety and/or rights-impacting AI.
Face Recognition/Face Capture (FR/FC)? No.
Use Case Name: Non-Intrusive Inspection (NII) 3D Imaging Tool
Use Case ID: DHS-163
Use Case Summary: CBP is responsible for the processing of imported mail, which includes, but is not limited to, the examination of commercial and personal parcels to detect contraband while assuring compliance with applicable laws and regulations. CBP uses a 3D imaging tool for border and transportation security. This system generates high resolution, rapid imaging of objects behind occlusions; creates 3D images for existing processes without significant slowdowns; and provides a novel narcotics detection capability for the inspection of packages. The system uses supervised ML-trained algorithms to accelerate identification of anomalies and objects of interest within the output images by CBP officers. Based on the output images, officers are able to triage incoming mail more effectively and make a faster determination of whether to apply additional screening., The solution utilizes AI/ML to generate high resolution, rapid imaging of objects behind occlusions; create 3D images for existing processes without significant slowdowns; and provide a novel narcotics detection capability for the inspection of packages. The system creates detection alerts for Items of Interest.
Use Case Topic Area: Law & Justice
Deployment Status: Implementation and Assessment
Safety- and/or rights-impacting? No
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Babel
Use Case ID: DHS-185
Use Case Summary: Babel is a commercially procured tool that helps CBP compile social media and open-source information on travelers who may be subject to further screening for potential violation of laws that CBP is authorized to enforce or administer. The tool searches and aggregates open-source information related to manually entered queries, which CBP can review and utilize to identify potential threats to the United States. CBP uses this tool to conduct targeted queries to aid CBP in open source research to monitor potential threats or dangers, or to identify travelers who may be subject to further inspection for violation of relevant laws . Babel utilizes AI modules for text detection and translation as well as object and image recognition to provide analysts with possible matches to manually review in a single interface, versus doing multiple manual queries. The output is not singly used for action or decision making. Rather, it is used to identify additional open source or social media content for a person or to identify additional selectors (such as phone and emails) that are previously unknown to CBP. These selectors are then compared by an analyst against Government systems to identify any additional derogatory information. These factors often eliminate additional screening for the traveler.
Use Case Topic Area: Law & Justice
Deployment Status: Implementation
Safety- and/or rights-impacting? Yes. Rights-impacting
Key Identified Risk & Mitigations: Forthcoming. Office of Management and Budget (OMB) approved a compliance extension through November 30, 2025. The requested extension is to provide time to get additional foundational information from the vendor, such as information about data provenance and training, model accuracy, and ongoing monitoring of model's performance.
Read more about safety and/or rights-impacting AI and compliance with required minimum risk management practices.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Airship Outpost for Cross Border Conveyance Identification
Use Case ID: DHS-188
Use Case Summary: CBP leverages Artificial Intelligence (AI) within the Airship Outpost system to identify and document cross-border conveyances, including aircraft, vessels, and automobiles. AI analyzes ingested images to determine the type of conveyance and locate the specific alphanumeric identifiers, such as tail numbers, hull numbers, or license plates, based on their unique placement standards. The system then captures these identifiers and assigns a confidence score to each detection, ensuring accurate documentation of cross-border activity in the database.
Use Case Topic Area: Law & Justice
Deployment Status: Deployed (Operation and Maintenance)
Safety- and/or rights-impacting? No. It was presumed rights-impacting relating to law enforcement in certain contexts, but the DHS Chief AI Officer determined this use case does not satisfy the definition of rights-impacting AI in M-24-10. This use case distinguishes between different types of conveyances and focuses on the appropriate location to capture the alphanumeric values used to identify the conveyance and add to a database on cross border activity. The AI associated with this use case does not produce alerts, or intelligence, related to the alphanumeric values. Read more about safety and/or rights-impacting AI.
Face Recognition/Face Capture (FR/FC)? No.
Use Case Name: Custom Broker License Exam Proctor Support
Use Case ID: DHS-310
Use Case Summary: CBP uses AI technology during the remote Customs Broker License Exam (CBLE) to alert exam proctors to activities that may need review (i.e., alerting the proctor when a candidate leaves or when a second person is present). The output of the AI is a box that highlights the examinee’s tile on the proctor’s screen, drawing the proctor’s attention to the examinee’s behavior. Proctors can use the third-party vendor portal to review the alerts. The examinee’s computer webcam and audio will be used to capture a video and audio recording of the examination by the vendor. After the alert, the proctor reviews the video and audio and determines if there is any potential violation of exam rules. If the proctor determines there is a potential violation, the proctor will create an incident report to describe the concern. Upon request, CBP will have access to the third-party vendor’s audio and video files to review along with any incident report.
Use Case Topic Area: Education & Workforce
Deployment Status: Deployed (Operation and Maintenance)
Safety- and/or rights-impacting? No. It was presumed rights-impacting relating to hiring and employment, but the DHS Chief AI Officer determined this use case does not satisfy the definition of rights-impacting AI in M-24-10. The AI system in this use case doesn’t rely on biometrics of any kind and alerts the proctor to indications of pre-determined activities that may need review. After the alert, the proctor reviews the video and audio and, based on what the proctor reviews, determines if there is any potential violation of exam rules. Read more about safety and/or rights-impacting AI.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: ERNIE
Use Case ID: DHS-315
Use Case Summary: ERNIE is used to analyze Radiation Portal Monitor (RPM) data to enhance the detection of radioactive materials. The system assesses potential threats, improving the accuracy and speed of identifying illicit or hazardous materials, thereby prioritizing high-risk detections, reducing false alarms and ensuring more efficient security and risk management at ports of entry. The model enhances threat detection and prioritizes high-risk targets, improving operational efficiency and national security. The model provides real-time risk assessments and alerts for potential threats detected by the Radiation Portal Monitors. It also provides prioritized recommendations for further screening based on the analysis of radiation data.
Use Case Topic Area: Law & Justice
Deployment Status: Operation and Maintenance
Safety- and/or rights-impacting? Yes. Safety- and rights-impacting
Key Identified Risks & Mitigations: This AI system has been tested in operational or real-world environments and risks have been identified and mitigated. Information about risks and mitigations for this use case may be law enforcement sensitive; DHS continues to review details for potential future disclosure in accordance with applicable law and policy.
Read more about safety and/or rights-impacting AI and compliance with required minimum risk management practices.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Unified Processing/Mobile Intake
Use Case ID: DHS-398
Use Case Summary: The Unified Processing/Mobile Intake system integrates with the Traveler Verification Service (TVS) to enhance border security operations. The system enables CBP personnel to match detainees' facial biometrics against CBP's photo galleries and derogatory image repositories. This process aids in identifying individuals with prior apprehensions and security concerns. The purpose is to facilitate the biometric identification of individuals as they are encountered by CBP for the purpose of expedited processing.
Use Case Topic Area: Law & Justice
Deployment Status: Operation and Maintenance
Safety- and/or rights-impacting? Yes. Rights-impacting
Key Identified Risks & Mitigations: This AI system has been tested in operational or real-world environments and risks have been identified and mitigated. Information about risks and mitigations for this use case may be law enforcement sensitive; DHS continues to review details for potential future disclosure in accordance with applicable law and policy.
Read more about safety and/or rights-impacting AI and compliance with required minimum risk management practices.
Face Recognition/Face Capture (FR/FC)? Yes. All Face Recognition and Face Capture (FR/FC) technology is tested both prior to operational use and at least every three years during operational use. DHS Science and Technology (S&T) oversees testing and evaluation based on International Organization for Standardization/ International Electrotechnical Commission (ISO/IEC) standards and technical guidance issued by National Institute of Standards and Technology (NIST). DHS S&T applies laboratory, scenario, and operational testing to cost-effectively characterize technology performance and, when feasible, disaggregate performance by user demographics such as gender, age, and skin tone.
Use Case Name: Cyber Threat Analysis (Recorded Future)
Use Case ID: DHS-399
Use Case Summary: Recorded Future data query enables CBP Cyber Threat Intelligence (CTI) analysts to focus on investigating recently observed relevant cyber threat activity rather than manually identifying, formatting, and searching for such information in multiple locations. Enables these analysts to quickly view known cyber threat activity targeting known vulnerabilities, which will reduce the time to identify risks to the vulnerabilities that exist in CBP’s information technology environment. AI/ML is employed several ways on this platform: For representation of structured knowledge of the world, using ontologies and events; for transforming unstructured text into a language-independent, structured representation, using natural language processing; for classifying events and entities, primarily to help decide if they are important enough to require a human analyst to perform a deeper investigation; to forecast events and entity properties by building predictive models from historic data. This service can also provide cyber risk scorecards for third party vendors, companies, and organizations.
Use Case Topic Area: Law & Justice
Deployment Status: Operation and Maintenance
Safety- and/or rights-impacting? No
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Vault Access Log (SPVAA)
Use Case ID: DHS-401
Use Case Summary: CBP uses the facial recognition technology in Seized Property Vault Activity Automation (SPVAA) to create a log of access to a seized property vault. Photos of the CBP personnel accessing the vault are loaded into the application and the application logs the entrance request, the case number associated with the entrance request, and the individual’s activity in the vault.
Use Case Topic Area: Mission-Enabling (internal agency support)
Deployment Status: Deployed (Operation and Maintenance)
Safety- and/or rights-impacting? No. It was presumed safety-impacting relating to controlling access to government facilities, but the DHS Chief AI Officer determined this use case does not satisfy the definition of safety-impacting AI in M-24-10. This use case provides a record-keeping function, not an access function. It does not manage or control access to the vault but replaces the manual logbook for logging CBP personnel as they access the associated vault. Read more about safety and/or rights-impacting AI.
Face Recognition/Face Capture (FR/FC)? Yes. All Face Recognition and Face Capture (FR/FC) technology is tested both prior to operational use and at least every three years during operational use. DHS Science and Technology (S&T) oversees testing and evaluation based on International Organization for Standardization/ International Electrotechnical Commission (ISO/IEC) standards and technical guidance issued by National Institute of Standards and Technology (NIST). DHS S&T applies laboratory, scenario, and operational testing to cost-effectively characterize technology performance and, when feasible, disaggregate performance by user demographics such as gender, age, and skin tone.
Use Case Name: CBP Employee Experience
Use Case ID: DHS-2373
Use Case Summary: The CBP Office of Human Resources Management (HRM) leverages Medallia Employee Experience Management Software to gather, analyze, and act on employee experience data from surveys and operational sources, providing real-time insights into the experiences of USBP recruits, applicants, and employees. Using Medallia’s Athena AI Text Analytics, qualitative feedback is layered with quantitative data to deliver comprehensive experience metrics. These insights enable HRM leadership to identify opportunities for process improvement, support congressionally mandated hiring targets, and enhance workforce retention. CBP HRM has implemented several Athena AI-powered solutions, including digital feedback surveys on the CBP Careers Site, post-application and withdrawal surveys, and feedback tools for critical hiring steps such as the medical exam and eQIP processes. Additionally, an exit survey gathers insights from departing employees to identify retention improvement opportunities. Together, these tools provide actionable data to refine recruitment processes, improve applicant and employee experiences, and strengthen overall workforce management.
Use Case Topic Area: Mission-Enabling (internal agency support)
Deployment Status: Operation and Maintenance
Safety- and/or rights-impacting? No
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Passive Body Scanner
Use Case ID: DHS-2380
Use Case Summary: Passive Body Scanner's (PBSs), deployed at various CBP pedestrian border crossings, use an algorithm to identify anomalies in body heat, assisting CBP officers to detect concealed weapons and contraband, allowing for efficient processing of travelers while flagging anomalies for further screening. While the AI provides these recommendations, CBP officers retain the final decision-making authority, reviewing any flagged areas to determine whether additional inspection is necessary. PBS is intended to enhance situational awareness in pedestrian traveler processing to aid CBP officers in observing potentially dangerous objects or contraband in a timely manner pursuant to CBP’s border search authority. This algorithm highlights areas on a person where potential objects may be blocking the subject's expected body heat and displays these areas on live video image, monitored by a CBP officer. The highlighted areas may show the locations of carried objects, which could be potential weapons or contraband.
Use Case Topic Area: Law & Justice
Deployment Status: Operation and Maintenance
Safety- and/or rights-impacting? Yes. Rights-impacting
Key Identified Risks & Mitigations: Forthcoming. Office of Management and Budget (OMB) approved a compliance extension through November 30, 2025. The requested extension is to provide time to get additional foundational information from the vendor, such as information about data provenance and training, model accuracy, and ongoing monitoring of model's performance.
Read more about safety and/or rights-impacting AI and compliance with required minimum risk management practices.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Unmanned Aircraft Collision Avoidance (Skydio)
Use Case ID: DHS-2383
Use Case Summary: Skydio X2D Small Unmanned Aircraft System (sUAS) platform operates on video feed only which in turn activates the obstacle avoidance on the unmanned aircraft where the AI capabilities are housed. The obstacle avoidance capability assists the pilot on the ground to avoid colliding the unmanned aircraft with objects such as man-made structures, vehicles, trees, wires, or other objects in the projected flight path. The pilot receives a visual alert on the hand controller, indicating a possible collision and in some cases the aircraft will slow down, change direction to avoid the obstacle, or stop.
Use Case Topic Area: Law & Justice
Deployment Status: Deployed (Operation and Maintenance)
Safety- and/or rights-impacting? No. It was presumed safety-impacting relating to controlling robot movement and autonomous/semi-autonomous vehicles, but the DHS Chief AI Officer determined this use case does not satisfy the definition of safety-impacting AI in M-24-10. The AI output in this use case is not used for the detection of items of interest in support of the border security mission. The AI output only provides collision avoidance for unmanned aircraft by assisting the pilot in avoiding obstacles such as small wires, tree limbs, or other objects. Read more about safety and/or rights-impacting AI.
Face Recognition/Face Capture (FR/FC)? No.
Use Case Name: CBP Translate
Use Case ID: DHS-2388
Use Case Summary: CBP Translate is a mobile and web application designed to assist officers in communicating with travelers who speak diverse languages during inspections at U.S. ports of entry. Built around the Google Translate API, it provides written and auditory translation services through a user-friendly interface available on Android, iOS, and web platforms. The app captures and stores written transcripts, audio recordings, document images, and travel document information to ensure accurate translations. CBP Translate enables officers to expedite basic questioning when human translation services are impractical or unavailable.
Use Case Topic Area: Law & Justice
Deployment Status: Operation and Maintenance
Safety- and/or rights-impacting? Yes. Rights-impacting
Key Identified Risks & Mitigations: Forthcoming. Office of Management and Budget (OMB) approved a compliance extension through November 30, 2025. The requested extension is to provide time to get additional foundational information from the vendor, such as information about data provenance and training, model accuracy, and ongoing monitoring of model's performance.
Read more about safety and/or rights-impacting AI and compliance with required minimum risk management practices.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Passenger Security Assessment Model (formerly Passenger Counternarcotics)
Use Case ID: DHS-2389
Use Case Summary: The Passenger Security Assessment Model employs advanced technology to identify potential risks in passenger crossings, focusing on various indicators of concern. This model is designed to support CBP personnel in quickly recognizing crossings that may warrant additional scrutiny, thereby enhancing border security and safety. By providing real-time evaluations of various risk factors, the model aids CBP personnel at ports of entry in making informed decisions. It leverages data that may not be readily available during initial processing, facilitating a thorough assessment of inbound travelers and vehicles. The key benefit of this system is improved detection capabilities, enabling personnel to efficiently identify individuals and vehicles that may require further investigation. The outputs include risk assessments and recommendations, which are integrated into existing passenger processing systems, such as the Automated Targeting System (ATS). These notifications equip CBP personnel with actionable insights to address potential security concerns in real-time.
Use Case Topic Area: Law & Justice
Deployment Status: Operation and Maintenance
Safety- and/or rights-impacting? Yes. Rights-impacting
Key Identified Risks & Mitigations: This AI system has been tested in operational or real-world environments and risks have been identified and mitigated. Information about risks and mitigations for this use case may be law enforcement sensitive; DHS continues to review details for potential future disclosure in accordance with applicable law and policy.
Read more about safety and/or rights-impacting AI and compliance with required minimum risk management practices.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Cargo Security Assessment Model (formerly Cargo Counternarcotics)
Use Case ID: DHS-2390
Use Case Summary: The Cargo Security Assessment Model is integrated within the Automated Targeting System (ATS) and utilizes advanced data analytics and machine learning techniques to evaluate shipments for potential risks. By analyzing various data sources, including shipping details and historical information, this tool enhances CBP’s ability to monitor cargo effectively while maintaining efficient processing. The system identifies shipments that may require further review, assisting CBP officers in their evaluations at Ports of Entry (POEs). When a shipment is flagged as high-risk, the results are returned to users as system alerts, which can be viewed in the associated results window. From this window, CBP operational personnel can assess the findings and determine the appropriate next steps, including potential inspections. Overall, the Cargo Assessment Tool strengthens operational capabilities and supports the detection of risks without compromising the efficiency of cargo processing.
Use Case Topic Area: Law & Justice
Deployment Status: Operation and Maintenance
Safety- and/or rights-impacting? Yes. Rights-impacting
Key Identified Risks & Mitigations: This AI system has been tested in operational or real-world environments and risks have been identified and mitigated. Information about risks and mitigations for this use case may be law enforcement sensitive; DHS continues to review details for potential future disclosure in accordance with applicable law and policy.
Read more about safety and/or rights-impacting AI and compliance with required minimum risk management practices.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Illicit Trade
Use Case ID: DHS-2391
Use Case Summary: CBP utilizes an advanced AI and machine learning model to enhance risk assessment in inbound cargo, focusing on critical areas related to priority trade initiatives. The system employs text analytics and predictive modeling to assist personnel in identifying suspicious shipments and flagging potential compliance issues for further examination. These efforts enable CBP to prioritize enforcement actions in cargo, targeting goods that may violate trade regulations through data-driven insights. The model identifies high-risk shipments to support CBP personnel in managing their workload associated with detecting threats and selecting candidate shipments for review and additional screening. By analyzing historical data, examination outcomes, and various risk attributes, the model helps identify shipments that may involve trade violations. The results generated by the model are sent to the Automated Targeting System for review and assessment by operational personnel, who may conduct further screening if necessary.
Use Case Topic Area: Law & Justice
Deployment Status: Operation and Maintenance
Safety- and/or rights-impacting? Yes. Rights-impacting
Key Identified Risks & Mitigations: This AI system has been tested in operational or real-world environments and risks have been identified and mitigated. Information about risks and mitigations for this use case may be law enforcement sensitive; DHS continues to review details for potential future disclosure in accordance with applicable law and policy.
Read more about safety and/or rights-impacting AI and compliance with required minimum risk management practices.
Face Recognition/Face Capture (FR/FC)? No
Use Case Name: Supervised Traveler Identity Verification Services (Officer Initiated)
Use Case ID: DHS-2412
Use Case Summary: Supervised Traveler Identity Verification Services (Officer Initiated) leverages facial recognition/comparison technology (FR/FC) to confirm the identity of travelers during traditional officer-led processing. In this system, a CBP officer uses FR/FC to compare a traveler's face to a gallery of stored images from prior government records, such as passports, visas, and previous border crossings. This technology supports officers in validating identities efficiently and accurately while maintaining oversight throughout the verification process. Officers remain responsible for making final determinations based on the results of the FR/FC and their observations, ensuring security and compliance., The TVS Biometric matching service is a cloud-based service that enables CBP to match a passenger’s identity against a trusted source, which improves traveler facilitation and reduces manual identity verification.
Use Case Topic Area: Law & Justice
Deployment Status: Operation and Maintenance
Safety- and/or rights-impacting? Yes. Rights-impacting
Key Identified Risks & Mitigations: This AI system has been tested in operational or real-world environments and risks have been identified and mitigated. Information about risks and mitigations for this use case may be law enforcement sensitive; DHS continues to review details for potential future disclosure in accordance with applicable law and policy.
Read more about safety and/or rights-impacting AI and compliance with required minimum risk management practices.
Face Recognition/Face Capture (FR/FC)? Yes.
All Face Recognition and Face Capture (FR/FC) technology is tested both prior to operational use and at least every three years during operational use. DHS Science and Technology (S&T) oversees testing and evaluation based on International Organization for Standardization/ International Electrotechnical Commission (ISO/IEC) standards and technical guidance issued by National Institute of Standards and Technology (NIST). DHS S&T applies laboratory, scenario, and operational testing to cost-effectively characterize technology performance and, when feasible, disaggregate performance by user demographics such as gender, age, and skin tone.
The DHS 2024 report on Use of Face Recognition and Face Capture Technologies provides additional information about use of FR/FC at DHS, including testing and evaluation of this use case.
Use Case Name: Semi-Supervised Traveler Identity Verification Services (Traveler Initiated)
Use Case ID: DHS-2413
Use Case Summary: The Semi-Supervised Traveler Identity Verification Services (Traveler Initiated) leverages biometric facial recognition to streamline identity verification at border crossings. Travelers submit images through self-service kiosks or mobile platforms, which are then compared against government databases, such as previous inspection records and travel documents, for identity confirmation and approval. This system enhances border efficiency and security by expediting processing while ensuring CBP officers maintain oversight to verify matches and address discrepancies. The TVS Biometric matching service is a cloud-based service that enables CBP to match a passenger’s identity against a trusted source, throughout the travel continuum which improves traveler facilitation and reduces manual identity verification.
Use Case Topic Area: Law & Justice
Deployment Status: Operation and Maintenance
Safety- and/or rights-impacting? Yes. Rights-impacting
Key Identified Risks & Mitigations: This AI system has been tested in operational or real-world environments and risks have been identified and mitigated. Information about risks and mitigations for this use case may be law enforcement sensitive; DHS continues to review details for potential future disclosure in accordance with applicable law and policy.
Read more about safety and/or rights-impacting AI and compliance with required minimum risk management practices.
Face Recognition/Face Capture (FR/FC)? Yes. All Face Recognition and Face Capture (FR/FC) technology is tested both prior to operational use and at least every three years during operational use. DHS Science and Technology (S&T) oversees testing and evaluation based on International Organization for Standardization/ International Electrotechnical Commission (ISO/IEC) standards and technical guidance issued by National Institute of Standards and Technology (NIST). DHS S&T applies laboratory, scenario, and operational testing to cost-effectively characterize technology performance and, when feasible, disaggregate performance by user demographics such as gender, age, and skin tone.
The DHS 2024 report on Use of Face Recognition and Face Capture Technologies provides additional information about use of FR/FC at DHS, including testing and evaluation of this use case.
Use Case Name: 3rd Party Traveler Identity Verification Services
Use Case ID: DHS-2414
Use Case Summary: 3rd Party Traveler Identity Verification Services is part of CBP’s Traveler Verification Service (TVS), a biometric system leveraging facial recognition technology (FRT). This system confirms traveler identities at various exit points, including airports, seaports, and land borders, as part of CBP’s Biometric Exit Program. These services operate under strict privacy guidelines to protect travelers’ personal information, aligning with CBP’s mission of balancing security and convenience., The TVS Biometric Air Exit solution is a cloud-based facial biometric matching service that enables CBP, External Partners, and Other Government Agencies (OGA) to match a passenger’s identity against a trusted source, throughout the travel continuum which improves traveler facilitation and reduces manual identity verification, Leverages DHS facial matching technologies to provide a match or no match response
Use Case Topic Area: Law & Justice
Deployment Status: Operation and Maintenance
Safety- and/or rights-impacting? Yes. Rights-impacting
Key Identified Risks & Mitigations: This AI system has been tested in operational or real-world environments and risks have been identified and mitigated. Information about risks and mitigations for this use case may be law enforcement sensitive; DHS continues to review details for potential future disclosure in accordance with applicable law and policy.
Read more about safety and/or rights-impacting AI and compliance with required minimum risk management practices.
Face Recognition/Face Capture (FR/FC)? Yes. All Face Recognition and Face Capture (FR/FC) technology is tested both prior to operational use and at least every three years during operational use. DHS Science and Technology (S&T) oversees testing and evaluation based on International Organization for Standardization/ International Electrotechnical Commission (ISO/IEC) standards and technical guidance issued by National Institute of Standards and Technology (NIST). DHS S&T applies laboratory, scenario, and operational testing to cost-effectively characterize technology performance and, when feasible, disaggregate performance by user demographics such as gender, age, and skin tone.
The DHS 2024 report on Use of Face Recognition and Face Capture Technologies provides additional information about use of FR/FC at DHS, including testing and evaluation of this use case.
Use Case Name: Mobile Traveler Identity Verification (ESTA Mobile and Mobile Passport Control)
Use Case ID: DHS-2415
Use Case Summary: CBP uses facial recognition technology for process efficiency under the Visa Waiver system, using Electronic System for Travel Authorization (ESTA) Mobile, and in identifying arriving travelers at airports of entry, using Mobile Passport Control. ESTA Mobile is an application and screening system used to determine whether citizens and nationals from countries participating in the Visa Waiver Program (VWP) are eligible to travel to the United States. ESTA Mobile extends the functionality to mobile platforms. The ESTA Mobile application captures a live photo from the traveler to perform a liveness test, and permit CBP’s TVS to conduct a 1-to-1 comparison of the traveler’s captured photo against the traveler’s passport e-Chip photo. ESTA mobile app users may either be an applicant, or third-party affiliates may complete an ESTA authorization on behalf of the traveler. If the ESTA Mobile output does not find liveness or cannot determine an identity match, the application can move forward through the ESTA website, simply treating it as filed by a third-party applicant. Mobile Passport Control captures lives photos of a traveler to permit CBP’s TVS to compare the photo to verified identifies compiled in flight galleries. This allows traveler to verify their identity using their mobile device. If a traveler is unsuccessful with mobile passport control, the traveler is simply processed in the regular customs line.
Use Case Topic Area: Law & Justice
Deployment Status: Deployed (Operation and Maintenance)
Safety- and/or rights-impacting? No. It was presumed rights-impacting relating to law enforcement in certain contexts, but the DHS Chief AI Officer determined this use case does not satisfy the definition of rights-impacting AI in M-24-10. For this use case, if the AI output prevents use of the mobile for identity verification, the individual proceeds with the usual process. In the case of a Visa Waiver application, the application moves forward through the ESTA website, simply treating it as filed by a third-party applicant. In the case of Mobile Passport Control, if a match is not returned, the traveler is simply processed in the regular customs line. Read about safety and/or rights-impacting AI.
Face Recognition/Face Capture (FR/FC)? Yes. All Face Recognition and Face Capture (FR/FC) technology is tested both prior to operational use and at least every three years during operational use. DHS Science and Technology (S&T) oversees testing and evaluation based on International Organization for Standardization/ International Electrotechnical Commission (ISO/IEC) standards and technical guidance issued by National Institute of Standards and Technology (NIST). DHS S&T applies laboratory, scenario, and operational testing to cost-effectively characterize technology performance and, when feasible, disaggregate performance by user demographics such as gender, age, and skin tone.
Use Case Name: Traveler Identity Verification Services (Vetting)
Use Case ID: DHS-2416
Use Case Summary: The Traveler Identity Verification Services (Vetting) uses biometric facial comparison technology to match traveler photographs with existing photographs in CBP’s holdings. These holdings include images captured during prior CBP inspections, U.S. passport and visa records, immigration records, and photographs from DHS encounters. This process is designed to complement the existing biographic vetting processes, enhancing identity verification and ensuring accurate assessments for travel and security purposes. CBP’s Traveler Identity Verification Services (Vetting) utilizes facial recognition technology to enhance threat identification by matching travelers’ biometrics against records of concern. When the system identifies a potential match to concerning records, CBP personnel conduct a manual facial comparison to determine whether the record is likely associated with the individual.
Use Case Topic Area: Law & Justice
Deployment Status: Operation and Maintenance
Safety- and/or rights-impacting? Yes. Rights-impacting
Key Identified Risks & Mitigations: This AI system has been tested in operational or real-world environments and risks have been identified and mitigated. Information about risks and mitigations for this use case may be law enforcement sensitive; DHS continues to review details for potential future disclosure in accordance with applicable law and policy.
Read more about safety and/or rights-impacting AI and compliance with required minimum risk management practices.
Face Recognition/Face Capture (FR/FC)? Yes. All Face Recognition and Face Capture (FR/FC) technology is tested both prior to operational use and at least every three years during operational use. DHS Science and Technology (S&T) oversees testing and evaluation based on International Organization for Standardization/ International Electrotechnical Commission (ISO/IEC) standards and technical guidance issued by National Institute of Standards and Technology (NIST). DHS S&T applies laboratory, scenario, and operational testing to cost-effectively characterize technology performance and, when feasible, disaggregate performance by user demographics such as gender, age, and skin tone.
In cases where we are leveraging the output of FR/FC from federal partners, we work closely with the Partner to ensure compliance with DHS policies on the use of FR/FC technologies.
Use Case Name: Process Efficiency Traveler Identity for Airline Check-in and Bag Drop
Use Case ID: DHS-2417
Use Case Summary: This use case utilizes facial comparison technology, Traveler Verification Service (TVS), for identity verification at check-in or bags drop for air travel. For bag drop, the Transportation Security Agency (TSA) has an established process under 49 U.S.C. § 114.1 for carriers to request an alternate procedure for identity verification. For these technical demonstrations, CBP’s TVS may serve as the requested alternate procedure. Air carriers, in voluntary partnership with CBP, may purchase camera equipment in order to capture photos at check-in and again at baggage drop for transmission to CBP. The TVS matching service creates a biometric template of each international traveler’s photo and compares it against templates of existing DHS holdings (i.e., U.S. passports, U.S. visas, and/or other DHS encounters) in order to provide identity verification on behalf of the CBP partner. In the event of a positive match, the TVS returns a unique identifier and matching results to the air carrier, and the traveler may proceed to finish the check-in/bag drop process. The matching result can be used by airlines (1) to meet their CBP regulatory requirement to verify specific passenger information and (2) their TSA regulatory requirement to accurately verify traveler’s identities. This is a voluntary opt-in process efficiency option provided to travelers.
Use Case Topic Area: Law & Justice
Deployment Status: Deployed (Operation and Maintenance)
Safety- and/or rights-impacting? No. It was presumed rights-impacting relating to law enforcement in certain contexts, risk assessments regarding immigration, and biometric identification in public spaces, but the DHS Chief AI Officer determined this use case does not satisfy the definition of rights-impacting AI in M-24-10. This use case provides biometric technology and the use of which is voluntary. If a traveler chooses to use it and the service cannot match a traveler, the traveler may continue check-in/bag drop via another means. CBP does not make any decision or action based on a no-match. Read more about safety and/or rights-impacting AI.
Face Recognition/Face Capture (FR/FC)? Yes. All Face Recognition and Face Capture (FR/FC) technology is tested both prior to operational use and at least every three years during operational use. DHS Science and Technology (S&T) oversees testing and evaluation based on International Organization for Standardization/ International Electrotechnical Commission (ISO/IEC) standards and technical guidance issued by National Institute of Standards and Technology (NIST). DHS S&T applies laboratory, scenario, and operational testing to cost-effectively characterize technology performance and, when feasible, disaggregate performance by user demographics such as gender, age, and skin tone.
Use Case Name: Autonomous Maritime Awareness
Use Case ID: DHS-P3
Use Case Summary: The Autonomous Maritime Awareness system combines surveillance towers, ocean data solutions, unmanned autonomous surface vehicles (ASV), and AI to autonomously detect, identify, and track items of interest in a maritime environment. The towers are low-cost, customizable, and relocatable surveillance systems. They are equipped with a suite of radars and day/night camera sensors. The ASVs have been ruggedized for the open ocean and are powered by wind, solar, and/or onboard engine as required, allowing them to operate in an area of responsibility (AOR) for up to 12 months. Their sensor suite includes cameras and radar. Both systems use AI/ML to detect and identify objects, determine items of interest (IoI) and autonomously track those items using their sensor suites. Once identified, these systems can send alerts to monitoring agencies for at-sea interdiction of potential targets and/or intel collections.
Deployment Status: Inactive (no longer used).
Use Case Name: Autonomous Aerostat
Use Case ID: DHS-23
Use Case Summary: Aerostat capability that uses three tethers instead of the traditional single tether, coupled with advanced weather sensors, analytic capabilities, and powerful winches. The AI/ML model is used to detect the need to launch and land based on weather. It also leverages AI and robotics to autonomously launch and recover the aerostat during inclement weather events without the need for on-site staffing, allowing the aerostat to operate autonomously, saving time and manpower.
Deployment Status: Inactive (no longer used)
Use Case Name: Geospatial Imagery Utilizing Annotation
Use Case ID: DHS-27
Use Case Summary: Leverages a commercial constellation of Synthetic Aperture Radar (SAR) satellites with readily available data, capable of imaging any location on Earth, day, and night, regardless of cloud cover. Utilizes AI, including machine vision, object, detection, object recognition, and annotation to detect airframes, military vehicles, and marine vessels, as well as built-in change detection capabilities for disaster response missions.
Deployment Status: Inactive (no longer used).
Use Case Name: Use of Technology to Identify Proof of Life
Use Case ID: DHS-28
Use Case Summary: Mobile applications rely on product for liveness detection to avoid use of spoofed or fraudulent images by bad actors. Being able to accept submitted data with confidence that the submitting individual is who and where they claim to be is critical to the functionality of the app within the agency environment.
Deployment Status: Inactive (consolidated with another use case). This use case was consolidated under CBP One (DHS-381).
Use Case Name: Integrated Digital Environment
Use Case ID: DHS-29
Use Case Summary: The Integrated Digital Environment provides managers with a better understanding of end user workflows, most and least used applications, and opportunities for improvement. The AI/ML model applies to end user activity data (e.g., use of applications, flow between applications) to help CBP identify opportunities for more efficient or effective configuration of interfaces, use of resources, or development and deployment of CBP’s applications. It tailors analytics and insight generation to allow metrics gathering, usage recording/observation, dashboarding, and workflow experimentations/suggestions to support analysts utilizing the entire suite of agency and open-source data systems. It also customizes existing capabilities to allow the exact automations needed for agency applications and systems, creating an integrated digital environment for greater connectivity and security between applications, and better ability for CBP administrators to manage and optimize use of applications by end users.
Deployment Status: Inactive (no longer used)
Use Case Name: AI Curated Synthetic Data
Use Case ID: DHS-31
Use Case Summary: AI Curated Synthetic Data creates synthetic data for computer vision to enable more capable and ethical AI when detecting anomalies in complex environments. Specifically, it creates an emulated X-ray sensor that can produce visually realistic synthetic X-ray scan images similar to real X-ray scan images, and virtual 3D assets of vehicles and narcotics containers. These images will be used to enhance the development of Anomaly Detection Algorithms for Non-Intrusive Inspection (NII), incorporating Artificial Intelligence/Machine Learning (AI/ML) for the detection of narcotics and other contraband in conveyances and cargo. The availability of rare event/outlier data or labeled data that can be used to train and automate detection is severely limited. The technology enhances available libraries of true positives and normal scans from CBP NII systems and supports development of Automated Threat Recognition (ATR) algorithms designed to quickly identify items of interest. Through the technology, the end user will have access to enhance existing, deployed algorithms to increase detection performance.
Deployment Status: Inactive (research and development only). This use case was reported in a previous version of the DHS AI Use Case Inventory but is a research and development use case that is not planned to be deployed.
Use Case Name: Data and Entity Resolution
Use Case ID: DHS-32
Use Case Summary: Product uses ML modeling to ingest multiple data sources and evolve models that associate disparate records to identify probable entities and/or identify commonalities between multiple independently submitted records. The automation of entity resolution within the models is supported by a tool that enables non-technical end users to continuously train models through a user-friendly interface.
Deployment Status: Inactive (no longer used)
Use Case Name: RVSS Legacy Overhauled System Project (INVNT)
Use Case ID: DHS-138
Use Case Summary: Video Computer Aided Detection (VCAD) (also known as Matroid AI) is software that enables CBP end users to create and share vision detectors. VCAD detectors are trained computer vision models that recognize objects, people, and events in any image or video stream. Once a detector is trained, it can monitor streaming video in real time, or efficiently search through pre-recorded video data or images to identify objects, people, and events of interest. Users can view detection information via a variety of reports and alert notifications to process and identify important events and trends. Detection data is also available through VCAD's powerful developer Application Programming Interface (API) and language specific clients, so CBP applications can be integrated with the power of computer vision.
Deployment Status: Inactive (consolidated with another use case). This use case was consolidated under Automated Item of Interest Detection (DHS-37).
Use Case Name: Agent Portable Surveillance
Use Case ID: DHS-162
Use Case Summary: The agent portable surveillance system is a backpack mobile unit meant for single agent deployments. The system identifies border activities of interest by using AI/ML to analyze data from Electro-Optical/Infra-Red cameras and radar. When an activity is detected, the system sends the information to agents through the Team Awareness Kit (TAK). Detections are shared with CBP TAK users to enhance efficiency and agent/officer safety.
Deployment Status: Inactive (no longer used)
Use Case Name: Open-source News Aggregation
Use Case ID: DHS-171
Use Case Summary: The platform enables users to make better decisions faster by identifying and forecasting emerging events on a global scale to mitigate risk, recognize threats, greatly enhance indications and warnings, and provide predictive intelligence capabilities. The AI/ML models enable rapid access to automated intelligence assessments by fusing, processing, exploiting and analyzing open sources of data (including news, social media, economic indicators, governance indicators, travel warnings, weather and other sources). This system is an immediate and substantial force multiplier that shifts the traditional approach of monitoring and assessing the operational environment to focus on the forecast of the future geopolitical, socio, and economic environment.
Deployment Status: Inactive (no longer used)
Use Case Name: Fivecast ONYX
Use Case ID: DHS-186
Use Case Summary: Fivecast is a technology platform accessed through an internet-based user interface that provides insight into a variety of social media platforms including, but not limited to, Facebook, Instagram, Telegram, and Twitter. Fivecast analyzes the strength of connections between social media users and collects both media and activity information from targeted profiles. It also enables the identification of usernames and profiles using individual names, telephone numbers, age, email address, and location. Fivecast has proven to be one of the most valuable tools in the OSINT technology stack as it enables advanced search, collection, and analysis of publicly available information through a single user interface, facilitating the collection of information regarding people, places, and things across social media platforms, as well as general information held on the surface, deep, and dark web to inform situational awareness. CBP uses Fivecast ONYX to analyze open-source data, including social media and other public platforms, to identify potential threats, monitor illegal activities, and assess risks to national security. The system enhances CBP's capability to monitor, analyze, and assess threats related to border security by processing vast amounts of open-source data. CBP aims to detect potential risks, monitor emerging trends, and uncover connections between individuals, organizations, or networks involved in illegal activities such as human trafficking, smuggling, or terrorism, thereby streamlining operations and bolstering security measures.
Deployment Status: Inactive (no longer used)
Use Case Name: Anomaly Detection in Non-Intrusive Inspection
Use Case ID: DHS-312
Use Case Summary: CBP intends to procure, develop, and implement solutions that leverage advanced algorithms and machine learning to analyze data to assist CBP personnel in automating analysis of non-intrusive inspection (NII) images used in cargo and vehicle inspections. The model will identify irregularities or deviations from expected patterns that may indicate concealed contraband or threats by displaying specific areas within scanned images that show anomalies, that possibly needing further screening. It is expected to reduce overall review time.
Deployment Status: Inactive (no longer used). This use case covered several Artificial Intelligence use cases which have been separated into individual entries: Anomaly Detection COV Structure (DHS-2363), Anomaly Detection Homogenous Cargo (DHS-2364), and Anomaly Detection POV Structure (DHS-2365)
Use Case Name: Port of Entry Risk Assessments
Use Case ID: DHS-343
Use Case Summary: CBP utilizes AI to develop, inform, and augment risk assessment processes that evaluate trade and travel data in real-time. AI methods are applied to CBP data holdings, and the results are used to inform decision making. These tools are continuously evaluated to ensure accuracy and precision, and support CBP’s core mission as part of the layered risk assessment strategy.
Deployment Status: Inactive (no longer used)
Use Case Name: Traveler Verification Service (TVS)
Use Case ID: DHS-344
Use Case Summary: The Traveler Verification Service (TVS) provides CBP a biometric entry/exit system to record arrivals and departures to and from the United States. CBP uses TVS as its backend matching service for all biometric entry and exit operations that use Facial Comparison. CBP creates localized photo "galleries" from images captured during previous entry inspections, photographs from U.S. passports and U.S. visas, and photographs from other DHS encounters. The images are converted into templates and the actual photograph is discarded. The templates are securely stored, and are what make up the TVS gallery. The templates are then used by the Facial Comparison system to verify a traveler's identity when they arrive or depart the U.S. When the traveler presents him or herself for entry, or for exit, the traveler will encounter a camera connected to TVS. This camera matches live images with the existing photo templates from passenger travel documents. Once the camera captures a quality image and the system successfully matches it with historical photo templates of all travelers from the gallery associated with that particular manifest, the traveler proceeds to inspection for admissibility by a CBP Officer, or exits the United States. For more information, please read the DHS/CBP/PIA-056 - Privacy Impact Assessment for the Traveler Verification Service.
Deployment Status: Inactive (no longer used). This use case covered several uses of face recognition/face capture (FR/FC) technology, TVS, and those FR/FC uses have been separated into individual, inventoried use cases such as Supervised Traveler Identity Verification Services (Officer Initiated) (DHS-2414)
Use Case Name: CBP One
Use Case ID: DHS-381
Use Case Summary: CBP One is a mobile application developed by CBP to streamline and enhance various border management processes. It allows users, including travelers and border agents, to access multiple CBP services through a single, user-friendly platform. The Traveler Verification System (TVS) is an AI-driven facial recognition technology integrated into CBP One. TVS uses facial recognition to compare live or uploaded images with CBP's database, enabling real-time identity verification. This automation streamlines border processes, enhances accuracy, and reduces fraud. The system outputs include identity match confirmation, fraud alerts, and traveler status updates for clearance in processes like boarding or border crossing.
Deployment Status: Inactive (no longer used)
Safety- and/or rights-impacting? Yes. Safety- and rights-impacting. This use case was identified as safety- and rights-impacting but was discontinued from use on 1/20/2025.
Use Case Name: I4 Viewer Matroid Image Analysis
Use Case ID: DHS-424
Use Case Summary: Matroid is a software that enables CBP end users to create and share vision detectors. Matroid detectors are trained computer vision models that recognize objects, people, and events in any image and in video streams. Once a detector is trained, it can monitor streaming video in real time, or efficiently search through pre-recorded video data or images to identify objects, people, and events of interest. Users can view detection information via a variety of reports and alert notifications to process and identify important events and trends. Detection data is also available through Matroid’s powerful developer Application Programming Interface and language-specific clients, so CBP applications can be integrated with the power of computer vision.
Deployment Status: Inactive (no longer used)
January 22nd, 2025
- [DHS-381] Deployment Status changed to Inactive (no longer used)
January 15th, 2025
- [DHS-24] Summary updated
- [DHS-80] Name changed to Traveler Entity Resolution, Summary updated
- [DHS-81] Name changed to Passport Anomaly Model, Summary updated
- [DHS-94] Name changed to Cargo Classification Tool, Summary updated
- [DHS-95] Name changed to Trade Entity Risk Model, Summary updated
- [DHS-183] Use Case Topic Area changed to Mission-Enabling (internal agency support)
- [DHS-186] Deployment Status changed to Inactive (no longer used)
- [DHS-188] Summary updated
- [DHS-312] Deployment Status changed to Inactive (no longer used)
- [DHS-317] Summary updated
- [DHS-2362] Summary updated
- [DHS-2367] Summary updated
- [DHS-2371] Summary updated
- [DHS-2373] Summary updated
- [DHS-2388] Summary updated
- [DHS-2389] Name changed to Passenger Security Assessment Model, Summary updated
- [DHS-2390] Name changed to Cargo Security Assessment Model, Summary updated
- [DHS-2391] Summary updated
- [DHS-2444] Summary updated
For other updates view the Full DHS AI Use Case Inventory on the DHS AI Use Case Inventory publication library.