Private Iris Recognition with High-Performance FHE

2026-01-24

AI Summary

This work proposes the first privacy-preserving iris matching scheme based on Threshold Fully Homomorphic Encryption (ThFHE) to address the risk of biometric privacy leakage in large-scale iris recognition. The approach requires no trusted setup, supports multi-party key sharing and public database queries, and provides active security. By optimizing linear algebra operations in the CKKS scheme, incorporating int8 GPU acceleration, and applying early ciphertext compression, the method substantially reduces computational overhead. On a system equipped with eight RTX 5090 GPUs, it achieves matching of 32 irises against a database of size \(7 \cdot 2^{14}\) in just 1.8 seconds, with only two to three rounds of communication.

Technology Category

• Machine Learning: Privacy
• Computer Vision: Bias, Fairness & Privacy
• Search and Optimization: Distributed Search

Application Category

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

Abstract

Among biometric verification systems, irises stand out because they offer high accuracy even in large-scale databases. For example, the World ID project aims to provide authentication to all humans via iris recognition, with millions already registered. Storing such biometric data raises privacy concerns, which can be addressed using privacy-enhancing techniques. Bloemen et al. describe a solution based on 2-out-of-3 Secret-Sharing Multiparty Computation (SS-MPC), for the World ID setup. In terms of security, unless an adversary corrupts 2~servers, the iris codes remain confidential and nothing leaks beyond the result of the computation. Their solution is able to match~$32$ users against a database of~$2^{22}$ iris codes in~$\approx 2$s , using~24 H100 GPUs, more than 40~communication rounds and $81$GB/party of data transferred (the timing assumes a network speed above~3Tb/s). In the present work, we explore the use of Threshold Fully Homomorphic Encryption (ThFHE) for the same task. The ThFHE solution brings a number of security advantages: no trusted setup, the encrypted database and queries can be public, the secret can be distributed among many parties, and active security can be added without significant performance degradation. Our proof-of-concept implementation of the computation phase handles $32$~eyes against a database of $7\cdot 2^{14}$ iris codes in~$\approx 1.8$s ($\approx 0.33s$ for 4 eyes against the same database), using 8 RTX-5090 GPUs. To this, one should add~2 to 3 rounds of communication (depending on deployment choice). We perform the matching using the CKKS (Th)FHE scheme. Our main technical ingredients are the use of recent progress on FHE-based linear algebra boosted using int8 GPU operations, and the introduction of a technique reducing the number of ciphertexts to be processed as early as possible.

Problem

• Private Iris Recognition
• Fully Homomorphic Encryption
• Biometric Privacy
• Secure Computation
• Large-scale Matching

Innovation

• Threshold FHE
• Private Iris Recognition
• CKKS
• GPU-accelerated FHE
• Ciphertext Reduction