Bridging Optimal Transport and Jacobian Regularization by Optimal Trajectory for Enhanced Adversarial Defense

Deep neural networks, particularly in vision tasks, are notably susceptible to adversarial perturbations. To overcome this challenge, developing a robust classifier is crucial. In light of the recent advancements in the robustness of classifiers, we delve deep into the intricacies of adversarial training and Jacobian regularization, two pivotal defenses. Our work is the first carefully analyzes and characterizes these two schools of approaches, both theoretically and empirically, to demonstrate how each approach impacts the robust learning of a classifier. Next, …

adversarial adversarial training challenge classifier classifiers cs.cv defense light networks neural networks regularization robust robustness tasks training trajectory transport vision