Reconstructing Protected Biometric Templates from Binary Authentication Results

2026-01-24

AI Summary

This study investigates whether the original biometric template protected by a binary (accept/reject) authentication system can be reconstructed solely from its feedback. To this end, the authors propose a novel attack that injects a large number of synthetic samples into the system and analyzes the resulting binary responses. By integrating generative inversion with optimization techniques, they establish a mapping pipeline from low-dimensional binary feedback to high-dimensional biometric features. This approach achieves, for the first time, near-lossless recovery of the original template using only binary authentication outcomes, enabling the synthesis of high-resolution, highly realistic facial images. Experimental results demonstrate negligible reconstruction loss and a success rate exceeding 98% in authenticating the generated images against the target system, thereby exposing significant privacy vulnerabilities inherent in current biometric authentication mechanisms that rely on binary feedback.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Privacy
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Biometric data is considered to be very private and highly sensitive. As such, many methods for biometric template protection were considered over the years -- from biohashing and specially crafted feature extraction procedures, to the use of cryptographic solutions such as Fuzzy Commitments or the use of Fully Homomorphic Encryption (FHE). A key question that arises is how much protection these solutions can offer when the adversary can inject samples, and observe the outputs of the system. While for systems that return the similarity score, one can use attacks such as hill-climbing, for systems where the adversary can only learn whether the authentication attempt was successful, this question remained open. In this paper, we show that it is indeed possible to reconstruct the biometric template by just observing the success/failure of the authentication attempt (given the ability to inject a sufficient amount of templates). Our attack achieves negligible template reconstruction loss and enables full recovery of facial images through a generative inversion method, forming a pipeline from binary scores to high-resolution facial images that successfully pass the system more than 98\% of the time. Our results, of course, are applicable for any protection mechanism that maintains the accuracy of the recognition.

Problem

• biometric template protection
• binary authentication results
• template reconstruction
• adversarial attacks
• privacy

Innovation

• biometric template reconstruction
• binary authentication attacks
• generative inversion
• template protection vulnerability
• adversarial biometric recovery