The Invisible Threat: Evaluating the Vulnerability of Cross-Spectral Face Recognition to Presentation Attacks

TL;DR

This paper investigates the security of NIR-VIS cross-spectral face recognition systems against presentation attacks, revealing vulnerabilities despite their robustness advantages, and highlights the need for improved defenses.

Contribution

It provides the first comprehensive empirical evaluation of presentation attack vulnerability in NIR-VIS cross-spectral face recognition systems.

Findings

Systems are somewhat reliable but vulnerable to specific attacks

NIR imaging offers robustness advantages but does not fully prevent attacks

Highlights the need for developing better anti-spoofing methods

Abstract

Cross-spectral face recognition systems are designed to enhance the performance of facial recognition systems by enabling cross-modal matching under challenging operational conditions. A particularly relevant application is the matching of near-infrared (NIR) images to visible-spectrum (VIS) images, enabling the verification of individuals by comparing NIR facial captures acquired with VIS reference images. The use of NIR imaging offers several advantages, including greater robustness to illumination variations, better visibility through glasses and glare, and greater resistance to presentation attacks. Despite these claimed benefits, the robustness of NIR-based systems against presentation attacks has not been systematically studied in the literature. In this work, we conduct a comprehensive evaluation into the vulnerability of NIR-VIS cross-spectral face recognition systems to presentation attacks. Our empirical findings indicate that, although these systems exhibit a certain degree of reliability, they remain vulnerable to specific attacks, emphasizing the need for further research in this area.