PAD-Phys: Exploiting Physiology for Presentation Attack Detection in Face Biometrics

TL;DR

This paper introduces three rPPG-based approaches for face presentation attack detection, demonstrating that transfer learning significantly improves detection accuracy and robustness against spoofing in face recognition systems.

Contribution

It proposes a novel transfer learning framework across physiological, Deepfakes, and presentation attack domains for enhanced face PAD using rPPG signals.

Findings

21.70% reduction in classification error rate with the presentation attack domain

Transfer learning improves detection accuracy and robustness

rPPG-based models are effective for PAD in non-copyable physiological features

Abstract

Presentation Attack Detection (PAD) is a crucial stage in facial recognition systems to avoid leakage of personal information or spoofing of identity to entities. Recently, pulse detection based on remote photoplethysmography (rPPG) has been shown to be effective in face presentation attack detection. This work presents three different approaches to the presentation attack detection based on rPPG: (i) The physiological domain, a domain using rPPG-based models, (ii) the Deepfakes domain, a domain where models were retrained from the physiological domain to specific Deepfakes detection tasks; and (iii) a new Presentation Attack domain was trained by applying transfer learning from the two previous domains to improve the capability to differentiate between bona-fides and attacks. The results show the efficiency of the rPPG-based models for presentation attack detection, evidencing a 21.70% decrease in average classification error rate (ACER) (from 41.03% to 19.32%) when the presentation attack domain is compared to the physiological and Deepfakes domains. Our experiments highlight the efficiency of transfer learning in rPPG-based models and perform well in presentation attack detection in instruments that do not allow copying of this physiological feature.