StyleAT: Defending Face Recognition Against Semantic Attacks
This work introduces BoundStyle, a potent semantic attack operating in StyleGAN's rich latent space to maximize misclassification rates and develops StyleAT, an efficient adversarial training scheme that incorporates low-budget attack variants yet defends against stronger and unseen semantic attacks.
Ben Shapira, Roi Cohen, Shang-Tse Chen et al.
· 0 citations