English

AdvFAS: A robust face anti-spoofing framework against adversarial examples

Computer Vision and Pattern Recognition 2024-04-26 v1 Artificial Intelligence

Abstract

Ensuring the reliability of face recognition systems against presentation attacks necessitates the deployment of face anti-spoofing techniques. Despite considerable advancements in this domain, the ability of even the most state-of-the-art methods to defend against adversarial examples remains elusive. While several adversarial defense strategies have been proposed, they typically suffer from constrained practicability due to inevitable trade-offs between universality, effectiveness, and efficiency. To overcome these challenges, we thoroughly delve into the coupled relationship between adversarial detection and face anti-spoofing. Based on this, we propose a robust face anti-spoofing framework, namely AdvFAS, that leverages two coupled scores to accurately distinguish between correctly detected and wrongly detected face images. Extensive experiments demonstrate the effectiveness of our framework in a variety of settings, including different attacks, datasets, and backbones, meanwhile enjoying high accuracy on clean examples. Moreover, we successfully apply the proposed method to detect real-world adversarial examples.

Keywords

Cite

@article{arxiv.2308.02116,
  title  = {AdvFAS: A robust face anti-spoofing framework against adversarial examples},
  author = {Jiawei Chen and Xiao Yang and Heng Yin and Mingzhi Ma and Bihui Chen and Jianteng Peng and Yandong Guo and Zhaoxia Yin and Hang Su},
  journal= {arXiv preprint arXiv:2308.02116},
  year   = {2024}
}
R2 v1 2026-06-28T11:47:50.800Z