Statistical Meta-Analysis of Presentation Attacks for Secure Multibiometric Systems

TL;DR

This paper introduces a statistical meta-model for face and fingerprint presentation attacks, enabling more accurate security evaluations of multibiometric systems against known and unknown fake trait attacks, and improving fusion rule robustness.

Contribution

It proposes a novel meta-model that captures a wider range of fake score distributions, including unknown attacks, enhancing security assessment and fusion rule design in multibiometric systems.

Findings

Meta-model reliably predicts system performance under unseen attacks.

Secure fusion rules show improved performance trade-offs.

Method can be extended to other biometric modalities.

Abstract

Prior work has shown that multibiometric systems are vulnerable to presentation attacks, assuming that their matching score distribution is identical to that of genuine users, without fabricating any fake trait. We have recently shown that this assumption is not representative of current fingerprint and face presentation attacks, leading one to overestimate the vulnerability of multibiometric systems, and to design less effective fusion rules. In this paper, we overcome these limitations by proposing a statistical meta-model of face and fingerprint presentation attacks that characterizes a wider family of fake score distributions, including distributions of known and, potentially, unknown attacks. This allows us to perform a thorough security evaluation of multibiometric systems against presentation attacks, quantifying how their vulnerability may vary also under attacks that are different from those considered during design, through an uncertainty analysis. We empirically show that our approach can reliably predict the performance of multibiometric systems even under never-before-seen face and fingerprint presentation attacks, and that the secure fusion rules designed using our approach can exhibit an improved trade-off between the performance in the absence and in the presence of attack. We finally argue that our method can be extended to other biometrics besides faces and fingerprints.