Optimizing DINOv2 with Registers for Face Anti-Spoofing

TL;DR

This paper introduces a DINOv2-based face anti-spoofing method that uses registers to enhance feature extraction and attention focus, effectively distinguishing live faces from spoofed images.

Contribution

The paper presents a novel DINOv2-based approach with registers for improved face anti-spoofing detection, emphasizing minute feature differences and attention suppression.

Findings

Effective detection on ICCV 2025 dataset

Superior performance over existing methods

Focuses on minute feature differences

Abstract

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. The project page is available at: https://gsisaoki.github.io/FAS-DINOv2-ICCVW/ .