Mind Your Margin and Boundary: Are Your Distilled Datasets Truly Robust?
Researchers have developed a new framework called Contrastive Curriculum for Robust Dataset Distillation (C$^2$R) to improve the robustness of distilled datasets. Unlike previous methods that treated all adversarial perturbations equally, C$^2$R prioritizes samples with the smallest robust margins and explicitly widens the separation between decision boundaries. This approach leads to better accuracy-robustness trade-offs, achieving superior robust accuracy across various datasets and attacks. AI