Bidirectional Biometric Authentication Using Transciphering and (T)FHE

2025-06-15

AI Summary

Biometric template leakage poses severe threats to user privacy and system security, yet practical deployment of fully homomorphic encryption (FHE) remains hindered by substantial ciphertext expansion, high key management overhead, and restrictive trust assumptions. To address these challenges, we propose a privacy-first bidirectional biometric authentication architecture, introducing the first Bidirectional Transciphering Framework (BTF). BTF synergistically integrates TFHE-based homomorphic computation, Trivium-enabled lightweight transciphering, and a non-colluding trusted party coordination mechanism. Our design ensures zero biometric template retention on the client side and prevents result forgery by the server, while simultaneously resolving three critical bottlenecks: ciphertext expansion, authentication repudiation, and key centralization. Evaluated on an iris dataset, our approach reduces communication overhead by 121× compared to standard FHE, significantly enhancing deployment feasibility and scalability.

Technology Category

• Computer Vision: Bias, Fairness & Privacy
• Machine Learning: Privacy
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy

Application Category

• Security and Privacy: Privacy-enhancing technologies
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Biometric authentication systems pose privacy risks, as leaked templates such as iris or fingerprints can lead to security breaches. Fully Homomorphic Encryption (FHE) enables secure encrypted evaluation, but its deployment is hindered by large ciphertexts, high key overhead, and limited trust models. We propose the Bidirectional Transciphering Framework (BTF), combining FHE, transciphering, and a non-colluding trusted party to enable efficient and privacy-preserving biometric authentication. The key architectural innovation is the introduction of a trusted party that assists in evaluation and key management, along with a double encryption mechanism to preserve the FHE trust model, where client data remains private. BTF addresses three core deployment challenges: reducing the size of returned FHE ciphertexts, preventing clients from falsely reporting successful authentication, and enabling scalable, centralized FHE key management. We implement BTF using TFHE and the Trivium cipher, and evaluate it on iris-based biometric data. Our results show up to a 121$ imes$ reduction in transmission size compared to standard FHE models, demonstrating practical scalability and deployment potential.

Problem

• Privacy risks in biometric authentication due to template leaks
• High overhead and trust limitations in Fully Homomorphic Encryption
• Scalability and efficiency challenges in encrypted biometric systems

Innovation

• Bidirectional Transciphering Framework combines FHE and transciphering
• Trusted party aids evaluation and key management
• Double encryption preserves FHE trust model