AI RESEARCH
OTAD: An Optimal Transport-Induced Robust Model for Agnostic Adversarial Attack
arXiv CS.LG
•
ArXi:2408.00329v2 Announce Type: replace Deep neural networks (DNNs) are vulnerable to small adversarial perturbations of the inputs, posing a significant challenge to their reliability and robustness. Empirical methods such as adversarial