Generalization Analysis for Adversarial Vision Transformer
TL;DR
This work establishes a high-probability generalization bound for ViTs in classification tasks under adversarial settings, and elucidates the roles of several factors in mitigating perturbation effects, norm regularization of weight matrices and depth-wise propagation constraints on layer-wise norms.
Abstract
Vision Transformers (ViTs) exhibit notable susceptibility to adversarial attacks, presenting a significant challenge for their deployment in security-sensitive applications. Despite their considerable empirical successes, a rigorous theoretical foundation for ViT's adversarial generalization behavior has not been adequately established. To address this limitation, we leverage empirical Rademacher complexity to analyze the mechanism of perturbation accumulation through deep ViTs layers. We establish a high-probability generalization bound for ViTs in classification tasks under adversarial settings. Our theoretical framework elucidates the roles of several factors in mitigating perturbation effects, norm regularization of weight matrices (in both MLP and attention modules) and depth-wise propagation constraints on layer-wise norms. Extensive experiments on benchmark datasets corroborate our theoretical insights, bridging the gap between ViTs architecture design and adversarial robustness.