Understanding Cross Domain Presentation Attack Detection for Visible Face Recognition

TL;DR

This paper proposes a novel cross-domain framework that enhances visible spectrum-based face presentation attack detection by leveraging infrared information during training, reducing the need for multi-spectral sensors.

Contribution

It introduces a new cross-domain detection framework, an inverse domain regularization technique, and a dense domain adaptation subnetwork for improved attack detection.

Findings

Enhanced discriminability of attack detection using only visible spectrum imagery.

Reduced reliance on multi-spectral sensors and computational resources.

Improved training stability through inverse domain regularization.

Abstract

Face signatures, including size, shape, texture, skin tone, eye color, appearance, and scars/marks, are widely used as discriminative, biometric information for access control. Despite recent advancements in facial recognition systems, presentation attacks on facial recognition systems have become increasingly sophisticated. The ability to detect presentation attacks or spoofing attempts is a pressing concern for the integrity, security, and trust of facial recognition systems. Multi-spectral imaging has been previously introduced as a way to improve presentation attack detection by utilizing sensors that are sensitive to different regions of the electromagnetic spectrum (e.g., visible, near infrared, long-wave infrared). Although multi-spectral presentation attack detection systems may be discriminative, the need for additional sensors and computational resources substantially increases complexity and costs. Instead, we propose a method that exploits information from infrared imagery during training to increase the discriminability of visible-based presentation attack detection systems. We introduce (1) a new cross-domain presentation attack detection framework that increases the separability of bonafide and presentation attacks using only visible spectrum imagery, (2) an inverse domain regularization technique for added training stability when optimizing our cross-domain presentation attack detection framework, and (3) a dense domain adaptation subnetwork to transform representations between visible and non-visible domains.