English

FaceGuard: A Self-Supervised Defense Against Adversarial Face Images

Computer Vision and Pattern Recognition 2021-04-07 v2

Abstract

Prevailing defense mechanisms against adversarial face images tend to overfit to the adversarial perturbations in the training set and fail to generalize to unseen adversarial attacks. We propose a new self-supervised adversarial defense framework, namely FaceGuard, that can automatically detect, localize, and purify a wide variety of adversarial faces without utilizing pre-computed adversarial training samples. During training, FaceGuard automatically synthesizes challenging and diverse adversarial attacks, enabling a classifier to learn to distinguish them from real faces and a purifier attempts to remove the adversarial perturbations in the image space. Experimental results on LFW dataset show that FaceGuard can achieve 99.81% detection accuracy on six unseen adversarial attack types. In addition, the proposed method can enhance the face recognition performance of ArcFace from 34.27% TAR @ 0.1% FAR under no defense to 77.46% TAR @ 0.1% FAR.

Keywords

Cite

@article{arxiv.2011.14218,
  title  = {FaceGuard: A Self-Supervised Defense Against Adversarial Face Images},
  author = {Debayan Deb and Xiaoming Liu and Anil K. Jain},
  journal= {arXiv preprint arXiv:2011.14218},
  year   = {2021}
}
R2 v1 2026-06-23T20:34:22.923Z