Optimizing DINOv2 with Registers for Face Anti-Spoofing
This addresses security vulnerabilities in face authentication systems against spoofing attacks, but it appears incremental as it builds on existing DINOv2 with modifications.
The paper tackled the problem of detecting spoofing attacks in face recognition systems by proposing a DINOv2-based method with registers to extract features and suppress attention perturbations, achieving effectiveness demonstrated through experiments on datasets from a workshop and SiW.
Face recognition systems are designed to be robust against variations in head pose, illumination, and image blur during capture. However, malicious actors can exploit these systems by presenting a face photo of a registered user, potentially bypassing the authentication process. Such spoofing attacks must be detected prior to face recognition. In this paper, we propose a DINOv2-based spoofing attack detection method to discern minute differences between live and spoofed face images. Specifically, we employ DINOv2 with registers to extract generalizable features and to suppress perturbations in the attention mechanism, which enables focused attention on essential and minute features. We demonstrate the effectiveness of the proposed method through experiments conducted on the dataset provided by ``The 6th Face Anti-Spoofing Workshop: Unified Physical-Digital Attacks Detection@ICCV2025'' and SiW dataset.