Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
Adaptive Debiasing Tsallis Entropy for Test-Time Adaptation
Xiangyu Wu, Dongming Jiang, Feng Yu +5
Mainstream Test-Time Adaptation (TTA) methods for adapting vision-language models, e.g., CLIP, typically rely on Shannon Entropy (SE) at test time to measure prediction uncertainty…
cs.CV2025
Who Can See Through You? Adversarial Shielding Against VLM-Based Attribute Inference Attacks
Yucheng Fan, Jiawei Chen, Yu Tian +1
As vision-language models (VLMs) become widely adopted, VLM-based attribute inference attacks have emerged as a serious privacy concern, enabling adversaries to infer private attri…
cs.CV2024
AutoBreach: Universal and Adaptive Jailbreaking with Efficient Wordplay-Guided Optimization
Jiawei Chen, Xiao Yang, Zhengwei Fang +4
Despite the widespread application of large language models (LLMs) across various tasks, recent studies indicate that they are susceptible to jailbreak attacks, which can render th…