01425nam a2200169 a 4500 20260901030330.0 250101s2020 xx o 000 0 eng d Danny Keller Fuzzy Commitments Offer Insufficient Protection to Biometric Templates Produced by Deep Learning arXiv 2020 text online resource In this work, we study the protection that fuzzy commitments offer when they are applied to facial images, processed by the state of the art deep learning facial recognition systems. We show that while these systems are capable of producing great accuracy, they produce templates of too little entropy. As a result, we present a reconstruction attack that takes a protected template, and reconstructs a facial image. The reconstructed facial images greatly resemble the original ones. In the simplest attack scenario, more than 78% of these reconstructed templates succeed in unlocking an account (when the system is configured to 0.1% FAR). Even in the "hardest" settings (in which we take a reconstructed image from one system and use it in a different system, with different feature extraction process) the reconstructed image offers 50 to 120 times higher success rates than the system's FAR. Open access — freely available to read. https://arxiv.org/pdf/2012.13293v1 Read the full paper (PDF) ERES 644 644 0 0 0 3 CYB MAIN MAIN SCICOMP 2026-09-01 0 YGE000905 2026-09-01 03:03:30 https://arxiv.org/pdf/2012.13293v1 2026-09-01 PAPER