BioZKFHE: Scalable Encrypted Biometric Identification via Verifiable Homomorphic Similarity Evaluation

2026-07-24

AI Summary

This work addresses the challenges of protecting template and query privacy while ensuring verifiable results in large-scale outsourced biometric identification. The authors propose an efficient and verifiable encrypted recognition scheme that integrates BGV homomorphic encryption, Double-CRT representation, and a Single-Coefficient Multi-Value (SCMV) packing strategy to substantially reduce storage and computational overhead. They further introduce a Proof-based Verifiable Similarity Computation (PVSC) method, which decomposes similarity computation into parallelizable proof instances. Combined with committee-assisted decryption and smart contract–based batch verification, the approach guarantees result correctness. Evaluated on FaceNet and MobileFaceNet, the scheme achieves near-lossless accuracy, reduces encrypted storage by 67%, and completes end-to-end verification in only 22–44 seconds for databases containing tens of thousands of templates.

Abstract

Large-scale biometric identification in outsourced settings requires two properties simultaneously: biometric templates and queries must remain protected during computation, and the encrypted similarity outputs produced by an untrusted compute node must be verifiably correct before any application result is released. Existing FHE-based biometric systems primarily address confidentiality, while practical verifiability introduces two bottlenecks in the underlying encrypted 1:N matching layer: rotation- and bandwidth-heavy similarity evaluation and the high cost of proving repeated homomorphic similarity traces. We present BioZKFHE, a framework for scalable encrypted biometric identification via verifiable homomorphic similarity evaluation that combines BGV homomorphic computation with committee-mediated proof opening/decryption and smart-contract verification of opened proof batches. To reduce encrypted storage and avoid rotation-heavy encrypted 1:N matching, we propose Single-Coefficient Multi-Value (SCMV) packing, which binds multiple quantized embedding values into each plaintext entry through base-T expansion. To make proof generation practical, we propose Parallelizable and Verifiable Similarity Computation (PVSC), which exploits the Double-CRT execution structure of BGV to decompose each blockwise similarity trace into parallel proof instances that are opened and checked before result release. Under standard lattice assumptions and explicit committee/verifier assumptions, we analyze recoverability, noise growth, confidentiality, encrypted-output integrity, and finalized-result integrity. Experiments on FaceNet and MobileFaceNet show near-lossless biometric utility, up to 67 percent encrypted-storage reduction, and about 22 to 44 seconds end-to-end proof-verified runtime for 10k to 40k templates.

Problem

• encrypted biometric identification
• verifiable computation
• homomorphic encryption
• outsourced biometrics
• similarity evaluation

Innovation

• verifiable homomorphic encryption
• encrypted biometric identification
• SCMV packing
• PVSC
• zero-knowledge proof