Login.gov: artificial intelligence technology used for detecting and mitigating fraud for remote unsupervised identity verification

Overview

Development stage

DeployedSource: c) Deployed – The use case is being actively authorized or utilized to support the functions or mission of an agency.

High-impact designation

Not reported

Impact justification

Not reported

Start date

Not reported

Withheld from public reporting

Not reported

Mission

Topic area

Service Delivery

Operational functions

Fraud, waste and improper payments, Biometrics and identity Derived by keyword rules; see methodology

Problem the AI is intended to solve

The AI is intended to solve the problem of detecting and mitigating fraud, spoofing, or deepfakes introduced by the remote identity proofing process. Specifically, it aims to compare and verify a user's identity by scanning identity documents uploaded online for authenticity, conducting one-to-one facial matching comparing the applicant’s self photograph (selfie) with the image on the identity evidence, performing liveness detection to mitigate imposters uploading images of stolen or counterfeit documents, and fraud detection analytics, all with the goal of ensuring the applicant is the person they are claiming to be. This is also to achieve NIST SP 800-63 compliance, which effectively requires AI-based capabilities for compliance with remote proofing.

Expected benefits

Not reported

System outputs

Not reported

Technology

AI classification

Computer visionSource: Computer Vision: AI that processes and interprets visual data (e.g., images and videos).

System name(s)

Not reported

Custom-developed code

Not reported

Public source code

Not reported

Sourcing

How it was built

Not reported

Vendor (as reported)

Not reported

Vendors (standardized)

None on the standard list

A vendor is the supplier named by the agency. It does not identify the underlying model or AI technology.

Data and privacy

Involves PII

Not reported

Privacy Impact Assessment

Not reported

Authorization to Operate

Not reported

Demographic features

Not reported

Training and evaluation data

Not reported

Federal Data Catalog

Not reported

Governance

0 of 8 minimum-practice questions answered. A blank answer means the agency reported nothing; it does not mean the practice is absent.

Potential impacts and how they were identified

Not reported