Deep CNN Face Matchers Inherently Support Revocable Biometric Templates

2025-06-23

AI Summary

Biometric templates are irreplaceable upon compromise, posing a fundamental security bottleneck in authentication systems. This paper proposes a cancelable biometrics framework leveraging an intrinsic property of deep convolutional neural network (CNN)-based face matchers: multiple functionally equivalent yet template-incompatible model instances—trained independently using the same architecture (e.g., ResNet)—enable secure template revocation and re-enrollment. Experiments demonstrate that feature vectors extracted by different instances for the same subject are mutually non-transferable; their cross-model similarity is even lower than intra-model similarity between different subjects, yielding a false match rate below 10⁻⁴. CNN backbones exhibit this property more readily than Vision Transformers (ViTs). Crucially, the method requires no architectural modifications or auxiliary transformations. It is the first work to systematically identify, characterize, and exploit the inherent template non-transferability of deep face matchers, establishing an efficient and practical new paradigm for cancelable biometric recognition.

Technology Category

• Computer Vision: Biometrics, Face, Gesture & Pose
• Machine Learning: Deep Neural Architectures and Foundation Models
• Natural Language Processing: Safety and Robustness

Application Category

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

Abstract

One common critique of biometric authentication is that if an individual's biometric is compromised, then the individual has no recourse. The concept of revocable biometrics was developed to address this concern. A biometric scheme is revocable if an individual can have their current enrollment in the scheme revoked, so that the compromised biometric template becomes worthless, and the individual can re-enroll with a new template that has similar recognition power. We show that modern deep CNN face matchers inherently allow for a robust revocable biometric scheme. For a given state-of-the-art deep CNN backbone and training set, it is possible to generate an unlimited number of distinct face matcher models that have both (1) equivalent recognition power, and (2) strongly incompatible biometric templates. The equivalent recognition power extends to the point of generating impostor and genuine distributions that have the same shape and placement on the similarity dimension, meaning that the models can share a similarity threshold for a 1-in-10,000 false match rate. The biometric templates from different model instances are so strongly incompatible that the cross-instance similarity score for images of the same person is typically lower than the same-instance similarity score for images of different persons. That is, a stolen biometric template that is revoked is of less value in attempting to match the re-enrolled identity than the average impostor template. We also explore the feasibility of using a Vision Transformer (ViT) backbone-based face matcher in the revocable biometric system proposed in this work and demonstrate that it is less suitable compared to typical ResNet-based deep CNN backbones.

Problem

• Addressing biometric compromise with revocable templates
• Generating multiple distinct yet equivalent face matcher models
• Comparing CNN and ViT backbones for revocable biometric systems

Innovation

• Deep CNN enables revocable biometric face templates
• Unlimited distinct models with equivalent recognition power
• Vision Transformer less suitable than ResNet backbones