Optimizing Key-Selection for Face-based One-Time Biometrics via Morphing

TL;DR

This paper introduces novel key-selection strategies at the signal level to enhance the security of face-based biometric systems against adversarial attacks, achieving significant attack mitigation while maintaining practicality.

Contribution

It proposes new key selection methods for cancelable face biometrics that effectively block adversarial attacks at the signal level, addressing a gap in existing privacy-focused systems.

Findings

Certain strategies completely block iterative adversarial attacks.

Attack success rate drops to about 5% with practical thresholds.

Signal-level key selection improves security without compromising usability.

Abstract

Nowadays, facial recognition systems are still vulnerable to adversarial attacks. These attacks vary from simple perturbations of the input image to modifying the parameters of the recognition model to impersonate an authorised subject. So-called privacy-enhancing facial recognition systems have been mostly developed to provide protection of stored biometric reference data, i.e. templates. In the literature, privacy-enhancing facial recognition approaches have focused solely on conventional security threats at the template level, ignoring the growing concern related to adversarial attacks. Up to now, few works have provided mechanisms to protect face recognition against adversarial attacks while maintaining high security at the template level. In this paper, we propose different key selection strategies to improve the security of a competitive cancelable scheme operating at the signal level. Experimental results show that certain strategies based on signal-level key selection can lead to complete blocking of the adversarial attack based on an iterative optimization for the most secure threshold, while for the most practical threshold, the attack success chance can be decreased to approximately 5.0%.