Robust optimization for adversarial learning with finite sample complexity guarantees

arXiv:2403.15207v1 Announce Type: new
Abstract: Decision making and learning in the presence of uncertainty has attracted significant attention in view of the increasing need to achieve robust and reliable operations. In the case where uncertainty stems from the presence of adversarial attacks this need is becoming more prominent. In this paper we focus on linear and nonlinear classification problems and propose a novel adversarial training method for robust classifiers, inspired by Support Vector Machine (SVM) margins. We view robustness under …

abstract adversarial adversarial attacks adversarial learning arxiv attacks attention case complexity cs.lg cs.sy decision decision making eess.sy making operations optimization robust sample type uncertainty view