Recent Advances in Adversarial Training for Adversarial Robustness

Adversarial examples for fooling deep learning models have been studied for several years and are still a hot topic. Adversarial training also receives enormous attention because of its effectiveness in defending adversarial examples. However, adversarial training is not perfect, many questions of which remain to solve. During the last few years, researchers in this community have studied and discussed adversarial training from various aspects. Many new theories and understandings of adversarial training have been proposed. In this survey, we systematically review the recent progress on adversarial training for the first time, categorized by different improvements. Then we discuss the generalization problems in adversarial training from three perspectives. Finally, we highlight the challenges which are not fully solved and present potential future directions.