Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
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…
cs.CV2026
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…
cs.CV2025
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…