4 papers
Proxy Robustness in Vision Language Models is Effortlessly Transferable
Xiaowei Fu, Fuxiang Huang, Lei Zhang
As a pivotal technique for improving the defense of deep models, adversarial robustness transfer via distillation has demonstrated remarkable success in conventional image classifi…
Adversarial Defense in Vision-Language Models: An Overview
Xiaowei Fu, Lei Zhang
The widespread use of Vision Language Models (VLMs, e.g. CLIP) has raised concerns about their vulnerability to sophisticated and imperceptible adversarial attacks. These attacks c…
Unsupervised Robust Domain Adaptation: Paradigm, Theory and Algorithm
Fuxiang Huang, Xiaowei Fu, Shiyu Ye +5
Unsupervised domain adaptation (UDA) aims to transfer knowledge from a label-rich source domain to an unlabeled target domain by addressing domain shifts. Most UDA approaches empha…
Rectifying Adversarial Sample with Low Entropy Prior for Test-Time Defense
Lina Ma, Xiaowei Fu, Fuxiang Huang +2
Existing defense methods fail to defend against unknown attacks and thus raise generalization issue of adversarial robustness. To remedy this problem, we attempt to delve into some…