用扩散模型生成逼真攻击样本，提升人脸识别防欺骗能力。
DiffFAS: Face Anti-Spoofing via Generative Diffusion Models
- 将图像质量作为先验信息输入网络，应对真实与伪造图像质量差异。
- 基于扩散模型生成高保真跨域、跨攻击类型的伪造人脸样本。
- 解决标注数据稀缺问题，适用于复杂场景下的防伪系统部署。
人脸反欺骗（FAS）在防止人脸识别系统遭受呈现攻击中至关重要。当前FAS系统面临域偏移问题，影响方法的泛化性能。本文重新审视域偏移的本质，将其分解为图像风格与图像质量两个因素：质量影响伪造信息的纯净度，风格则影响伪造信息的表现方式。基于此分析，提出DiffFAS框架，将图像质量作为先验信息输入网络以应对质量域偏移，并采用基于扩散的高保真跨域、跨攻击类型生成方法应对风格域偏移。DiffFAS可将易获取的真实人脸转化为具有精确标签的高质量伪造人脸，同时保持真实与伪造人脸身份一致性，缓解现有FAS系统在新型攻击样本标注数据不足的问题。在多个挑战性的跨域与跨攻击类型FAS数据集上验证了该框架的有效性，达到当前最优性能。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。