DiffFAS: Face Anti-Spoofing via Generative Diffusion Models

TL;DR

DiffFAS introduces a diffusion model-based framework for face anti-spoofing that addresses domain shift by modeling image style and quality, generating high-fidelity attack faces to improve generalization and reduce data scarcity.

Contribution

The paper proposes a novel diffusion-based approach that explicitly models style and quality shifts, enhancing cross-domain and cross-attack face anti-spoofing performance.

Findings

Achieves state-of-the-art results on challenging datasets.

Effectively generates high-fidelity attack faces with precise labels.

Reduces the impact of domain shift and data scarcity in FAS.

Abstract

Face anti-spoofing (FAS) plays a vital role in preventing face recognition (FR) systems from presentation attacks. Nowadays, FAS systems face the challenge of domain shift, impacting the generalization performance of existing FAS methods. In this paper, we rethink about the inherence of domain shift and deconstruct it into two factors: image style and image quality. Quality influences the purity of the presentation of spoof information, while style affects the manner in which spoof information is presented. Based on our analysis, we propose DiffFAS framework, which quantifies quality as prior information input into the network to counter image quality shift, and performs diffusion-based high-fidelity cross-domain and cross-attack types generation to counter image style shift. DiffFAS transforms easily collectible live faces into high-fidelity attack faces with precise labels while maintaining consistency between live and spoof face identities, which can also alleviate the scarcity of labeled data with novel type attacks faced by nowadays FAS system. We demonstrate the effectiveness of our framework on challenging cross-domain and cross-attack FAS datasets, achieving the state-of-the-art performance. Available at https://github.com/murphytju/DiffFAS.