BioZKFHE: Scalable Encrypted Biometric Identification via Verifiable Homomorphic Similarity Evaluation

Cancelable Biometric Authentication with Decentralized Template Protection Using Blockchain, IPFS, and Deep Face Embeddings

GoldenRetriever: Non-Interactive Homomorphic Encrypted Retrieval for Privacy-Preserving RAG

This work proposes a practical non-interactive encrypted retrieval framework for RAG based on threshold selection, and introduces a precision-stable mask polarization method that ensures accurate recovery of selected documents.

Securing Iris Recognition with Fully Homomorphic Encryption: Dimensionality Reduction in Iris Codes

Biometric recognition systems are fundamental to modern identity management and access control. However, the security and privacy of these systems are severely compromised when adversaries gain access to stored biometric templates, given the immutable link between individuals and their biometric traits. This study presents a benchmark analysis of the trade-offs between dimensionality and system performance in the context of securing iris biometric templates using Fully Homomorphic Encryption (FHE). We examine the impact of Principal Component Analysis (PCA) as a dimensionality reduction technique to enable encrypted-domain computation while maintaining recognition accuracy and reducing computational overhead. In lieu of introducing a new dimensionality reduction technique, this study rigorously benchmarks the applicability of PCA in balancing computational efficiency and recognition accuracy for biometric systems operating under Fully Homomorphic Encryption (FHE) constraints. We evaluate our method on various iris databases, including CASIA-V1, CASIA-V3, UBATH, and IITD. Our approach achieves a 100% True Acceptance Rate (TAR) on CASIA-V1, CASIA-V3, and UBATH and a 99.38% TAR on the IITD database at a 0.1% False Accept Rate (FAR), with a feature dimensionality of 250. This work advances iris recognition security by combining privacy measures with dimensionality reduction for improved authentication accuracy.

Layer-aware deep feature optimization for privacy-preserving face biometrics with revocable key binding

Biometric cryptosystems designed with revocability and session-level renewability must preserve template privacy and maintain reliable authentication despite the inherent variability of biometric data. A key unresolved issue in deep biometric protection is how the embedding should be formed from a network’s final representation for secure cryptographic key binding. This study presents a privacy-preserving face biometric framework in which deep embeddings are transformed into binary revocable templates and bound on the fly to cryptographic keys using a fuzzy commitment scheme with error-correcting codes. This work focuses on revocability and session-level renewability; achieving full ISO/IEC 24745 cancelability (specifically unlinkability and irreversibility) requires a keyed transform and salted-hashed storage, which we identify as essential future work. Holding the trained network and the binding pipeline fixed, three feature-aggregation strategies applied to the final representation are systematically compared, namely Global Average Pooling, Smoothed Flattening, and a dedicated Dense Feature Layer. The resulting templates are combined with Reed–Solomon and Extended Hamming coding schemes to analyse the trade-offs among discriminability, error tolerance, key length, and computational cost. Experiments conducted on the FEI Face Database show that the Dense Feature Layer (a learned non-linear projection) provides a markedly more suitable representation for secure key binding than the non-learned spatial-aggregation alternatives, achieving the best authentication performance among the tested alternatives. At the selected operating point under controlled-acquisition, frontal-face conditions, the protected system achieves a 0% false acceptance rate (95% confidence interval [0%, 0.92%], n = 400) with a 1360-bit bound key while maintaining a genuine acceptance rate of 91.0% with Reed–Solomon coding and 89.75% with Extended Hamming coding in the structurally secure independent-segment configuration, which eliminates key-reuse leakage. On the deployment side, mobile-side binding completes in well under a millisecond for both codes, whereas cloud-side decoding differs sharply: Reed–Solomon requires 15.056 ms per attempt against 0.042 ms for Extended Hamming, a≈ 350 × gap that dominates one-to-many scalability. The results further show that Reed–Solomon coding is preferable for high-security low-scale verification, whereas Extended Hamming coding offers substantially lower cloud-side decoding cost and better scalability for one-to-many identification. Consequently, the relative ranking of the three strategies, rather than the absolute error rates, is the primary transferable finding. Overall, the study provides practical design guidance for jointly selecting CNN feature representations and cryptographic binding mechanisms in secure and privacy-preserving biometric authentication systems.

Decentralized Biometric Authentication via Threshold-Based Key Derivation †

Biometric authentication offers enhanced usability for digital payments, but traditional centralized architectures suffer from single points of failure. While blockchain integration promises decentralized trust, existing solutions often store biometric helper data (e.g., fuzzy commitments) directly on-chain. We demonstrate that such transparency, even in permissioned settings, exposes low-entropy biometric inputs to offline brute-force attacks and identity-linkage risks if the immutable ledger is accessed by malicious nodes. To resolve this transparency–privacy paradox, we propose a threshold-based decentralized authentication framework. Unlike prior works, our protocol keeps all sensitive Biometric-Enhanced Key Derivation (BEKD) tokens entirely off-chain, using the blockchain solely for freshness enforcement. We provide a game-based security analysis of brute-force resistance, unforgeability, and unlinkability. Our experimental results demonstrate that our scheme’s gas cost is acceptable, offering a robust solution for self-sovereign biometric identity.

Ciphertext-Native Watermarking for RLWE-Based Homomorphic Encryption

This work proposes a watermarking technique for RLWE-based HE ciphertexts by exploiting the algebraic structure of RLWE polynomials and introduces two practical schemes that preserve the original security of HE while maintaining correctness and watermark robustness.