2026
FERD: Fairness-Enhanced Data-Free Adversarial Robustness Distillation
ICLR 2026poster
Data-Free Robustness Distillation (DFRD) aims to transfer the robustness from the teacher to the student without accessing the training data. While existing methods focus on overall robustness, they overlook the robust fairness issues, leading to severe disparity of robustness across different categ…