Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
Break the Brake, Not the Wheel: Untargeted Jailbreak via Entropy Maximization
Mengqi He, Xinyu Tian, Xin Shen +6
Recent studies show that gradient-based universal image jailbreaks on vision-language models (VLMs) exhibit little or no cross-model transferability, casting doubt on the feasibili…
cs.CV2025
High-Entropy Tokens as Multimodal Failure Points in Vision-Language Models
Mengqi He, Xinyu Tian, Xin Shen +4
Vision-language models (VLMs) achieve remarkable performance but remain vulnerable to adversarial attacks. Entropy, as a measure of model uncertainty, is highly correlated with VLM…
cs.CV2025
Trust-Aware Diversion for Data-Effective Distillation
Zhuojie Wu, Yanbin Liu, Xin Shen +2
Dataset distillation compresses a large dataset into a small synthetic subset that retains essential information. Existing methods assume that all samples are perfectly labeled, li…