Towards Fairness-Aware Adversarial Learning

arXiv:2402.17729v1 Announce Type: new
Abstract: Although adversarial training (AT) has proven effective in enhancing the model's robustness, the recently revealed issue of fairness in robustness has not been well addressed, i.e. the robust accuracy varies significantly among different categories. In this paper, instead of uniformly evaluating the model's average class performance, we delve into the issue of robust fairness, by considering the worst-case distribution across various classes. We propose a novel learning paradigm, named Fairness-Aware Adversarial Learning (FAAL). As a …

abstract accuracy adversarial adversarial learning adversarial training arxiv class cs.cv fairness issue paper performance robust robustness training type