Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
Feature-Aware Token Attack for Compression-Triggered Stealthy Failures in Large Vision-Language Models
Shilinlu Yan, Bowen Chen, Yuechen Zhang +3
Visual-token compression improves the efficiency of large vision-language models, but can expose failures that full-token evaluation misses. We study adversarial images that preser…
cs.CV2026
Still There, No Longer Seen: Exposing Compression-Induced Risk in Large Vision-Language Models
Qiankun Li, Yuechen Zhang, Bowen Chen +4
Visual token compression reduces the inference cost of Large Vision-Language Models (LVLMs). However, aggregate robustness measures do not reveal whether a particular adversarial f…
cs.CV2026
Structure-Guided Visual Perturbation Neutralization for LVLMs
Yuanhe Zhang, Xueting Wang, YanBin Ren +6
Image inputs enable Large Vision Language Models (LVLMs) to perceive fine-grained visual information, but also introduce a pixel-level attack surface through which adversarial pert…