FaceGuard: A Self-Supervised Defense Against Adversarial Face Images

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.