From Classification to Consistent Templates: Multiple Permuted-Label Classifier Encoding for Biometric Template Protection

2026-07-15

AI Summary

This work addresses the challenge of biometric template protection, which must tolerate intra-class variations while preventing information leakage—a balance often unmet by existing methods that rely on auxiliary data, preserve exploitable similarity structures, or are confined to specific modalities. The authors propose a unified protection framework based on multi-classifier label permutation encoding: stable outputs from identity classifiers are transformed via label permutation to expand the candidate space, and exact matching is achieved without error-correcting codes or auxiliary data through template concatenation, XOR randomization, and cryptographic hashing. The scheme guarantees irreversibility, revocability, and non-linkability, demonstrating strong performance across four face and two iris datasets—achieving 98.61% GAR at a FAR of 5.51×10⁻⁵% on YTF and 99.10% GAR at 0.00% FAR on CASIA-Iris-Lamp.

Abstract

Biometric template protection (BTP) must secure stored templates while tolerating intra-class variations. Existing methods rely on protected-domain similarity matching, error correction, or predefined-template mappings, potentially retaining exploitable similarity structures, introducing helper-data risks, depending on artificial targets, or coupling protection to specific modalities. Storing only cryptographic hash digests eliminates directly comparable representations and conceals pre-hash templates, but hash-based exact-match verification requires genuine samples to generate identical intermediate templates before hashing. Identity classification is naturally suited to this requirement because it maps variable biometric samples to stable and discriminative identity-level outputs. Based on this insight, we propose Multiple Permuted-Label Classifier Encoding (MPLCE). Through classifier-specific label permutations, MPLCE assigns each identity different labels across multiple classifiers. The predicted labels are encoded and concatenated to form an intermediate template, preventing repeated encodings of a single identity label and enlarging the effective candidate space while preserving classification consistency. The template is randomized with an application-specific XOR string and cryptographically hashed, enabling exact-match verification without error correction codes or biometric-dependent helper data. Using modality-specific classifiers, MPLCE retains the same template generation and protection procedure across modalities. On four face and two iris datasets, MPLCE achieves competitive performance, including a GAR of 98.61\% at a FAR of 5.51\(\times\)10\textsuperscript{-5}\% on YTF and a GAR of 99.10\% at a FAR of 0.00\% on CASIA-Iris-Lamp. Security analyses and attack evaluations support its irreversibility, revocability, and unlinkability under the threat model.

Problem

• Biometric template protection
• Intra-class variations
• Security
• Template revocability
• Unlinkability

Innovation

• Biometric Template Protection
• Multiple Permuted-Label Classifier Encoding
• Cryptographic Hashing
• Cross-Modal Consistency
• Exact-Match Verification