Improving Robust Fairness via Balance Adversarial Training. (arXiv:2209.07534v1 [cs.LG])

Adversarial training (AT) methods are effective against adversarial attacks,
yet they introduce severe disparity of accuracy and robustness between
different classes, known as the robust fairness problem. Previously proposed
Fair Robust Learning (FRL) adaptively reweights different classes to improve
fairness. However, the performance of the better-performed classes decreases,
leading to a strong performance drop. In this paper, we observed two unfair
phenomena during adversarial training: different difficulties in generating
adversarial examples from each class (source-class fairness) and disparate
target class …

adversarial balance fairness training