No abstract

Based on the significant improvement of model robustness by AT (Adversarial Training), various variants have been proposed to further boost the performance. Well-recognized methods have focused on different components of AT (e.g., designing loss functions and leveraging additional unlabeled data). It is generally accepted that stronger perturbations yield more robust models. However, how to generate stronger perturbations efficiently is still missed. In this paper, we propose an efficient automated attacker called A 2 to boost AT by generating the optimal perturbations on-the-fly during training. A 2 is a parameterized automated attacker to search in the attacker space for the best attacker against the defense model and examples. Extensive experiments across different datasets demonstrate that A 2 generates stronger perturbations with low extra cost and reliably improves the robustness of various AT methods against different attacks.