🔐

FaceAuth

Biometric OAuth2 Authentication Provider

Status Research / Archived
Year 2024
Category Security Innovation
View Details Back to Projects

Project Status: This research project has been archived in favor of FraudLens, which demonstrated stronger product-market fit and enterprise demand. The learnings from FaceAuth's security and authentication architecture inform the FraudLens security implementation.

The Vision

FaceAuth was a research project exploring biometric authentication as a replacement for passwords. The hypothesis: facial recognition combined with liveness detection could provide both stronger security and better user experience than traditional credentials.

Technical Approach

FaceAuth implemented a complete OAuth2-compliant authentication provider. Users authenticate using facial recognition via AWS Rekognition. The system includes deepfake detection, liveness checking, and enterprise-grade security patterns. All interactions are secured with JWT tokens and standard OAuth2 flows.

Why We Archived This Project

While FaceAuth demonstrated strong technical achievement, market research revealed limited near-term adoption. Enterprise security teams remain risk-averse with biometric authentication. FraudLens, conversely, addresses a clearly quantified problem (€20B annual fraud) with immediate ROI. This decision reflects pragmatism: building what markets need, not just what's technically interesting.

Technical Architecture

OAuth2 Implementation

Standard OAuth2 Authorization Code Flow with biometric authentication at the credential exchange step.

  • Authorization Endpoint: Returns OAuth2 authorization code after facial verification
  • Token Endpoint: Exchanges authorization code for JWT access tokens
  • Facial Recognition: AWS Rekognition with face matching and deepfake detection
  • Liveness Detection: Challenge-response system to prevent photo spoofing
  • Token Management: JWT with standard claims (sub, exp, aud, iss)

Tech Stack

  • Language: Java 17+
  • Framework: Spring Boot 3.x with Spring Security
  • Authentication: Custom OAuth2 Provider implementation
  • Tokens: JWT (io.jsonwebtoken library)
  • Biometric API: AWS Rekognition
  • Database: PostgreSQL for user sessions and audit logs
  • Testing: JUnit 5, Mockito, comprehensive security tests
  • Deployment: Docker, AWS App Runner

Key Technical Features

🔍 Facial Recognition

AWS Rekognition provides highly accurate face matching. System stores face embeddings for registered users and compares against login attempt images.

👥 Deepfake Detection

Detects spoofing attempts using high-quality photos or deepfake videos. Confidence scoring indicates likelihood of genuine authentication.

✨ Liveness Checking

Challenge-response system requires users to perform actions (smile, blink, turn head) to prove they're providing live face. Prevents static image attacks.

🔐 OAuth2 Compliance

Full OAuth2 provider implementation. Compatible with any client supporting standard OAuth2 flows. Generates standards-compliant JWT tokens.

📊 Audit Logging

Complete audit trail of all authentication attempts. Logs successful logins, failed attempts, and confidence scores for security analysis.

🛡️ Security First

Enterprise security patterns: CORS configuration, CSRF protection, rate limiting, secure token storage, and TLS-only communication.

Research Results

98%
Face Matching Accuracy

On AWS Rekognition benchmark

100+
Deepfake Scenarios Tested

Photos, videos, masks

<2s
Auth Response Time

Face capture to token generation

5
Security Layers

Face match + Liveness + Deepfake

Technical & Strategic Learnings

🔐 OAuth2 Deep Dive

Implementing OAuth2 from scratch taught nuances: authorization codes, token lifetimes, refresh token rotation, and scope management. Critical for understanding enterprise authentication.

🤖 AWS Rekognition Integration

Face embeddings, confidence scoring, and the "detect" vs "recognize" distinction. Learned that perfect accuracy is impractical—must balance false positives/negatives.

🎭 Spoofing & Deepfake Reality

Research revealed that deepfake detection is not a solved problem. Liveness detection helps but isn't foolproof. Enterprise adoption requires acceptance of residual risk.

💼 Product-Market Fit Matters

The biggest learning: technical achievement doesn't equal market success. FaceAuth was technically sound but lacked enterprise demand. FraudLens solves a quantifiable problem—crucial difference.

How FaceAuth Informed FraudLens

Security Architecture

FaceAuth's security-first patterns directly inform FraudLens. Multi-layered validation approach (parts + labor + phantom work + history) mirrors FaceAuth's layered authentication (face + liveness + deepfake).

AWS Service Integration

Experience with AWS Rekognition made transitioning to Textract and Bedrock natural. Similar patterns for service integration, error handling, and cost optimization.

Enterprise Thinking

FaceAuth forced engagement with enterprise security concerns. This mindset transfers to FraudLens: GDPR compliance, data retention, audit logging, and risk assessment.

Interested in This Approach?

While FaceAuth is archived, the security and authentication patterns remain valuable for enterprise applications. Learn more about my approach to secure system design.