Sensitivity as a Double-Edged Sword: A Trade-off Between Discriminability and Adversarial Robustness 事件

Sensitivity as a Double-Edged Sword: A Trade-off Between Discriminability and Adversarial Robustness arXiv:2606.01746v1 Announce Type: new Abstract: Modern neural networks are highly susceptible to adversarial perturbations. In this work, we identify that part of this vulnerability stems from the sensitivity of the widely used fully connected (FC) classifiers to such perturbations. In contrast, simple $\ell_2$ distance-based classifiers exhibit significantly greater robustness. We provide thoro