6 papers
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…
Safe-FedLLM: Delving into the Safety of Federated Large Language Models
Mingxiang Tao, Yu Tian, Wenxuan Tu +3
Federated learning (FL) addresses privacy and data-silo issues in the training of large language models (LLMs). Most prior work focuses on improving the efficiency of federated lea…
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…
Red Teaming Large Reasoning Models
Jiawei Chen, Yang Yang, Chao Yu +6
Large Reasoning Models (LRMs) have emerged as a powerful advancement in multi-step reasoning tasks, offering enhanced transparency and logical consistency through explicit chains o…
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…
BSPA: Exploring Black-box Stealthy Prompt Attacks against Image Generators
Yu Tian, Xiao Yang, Yinpeng Dong +3
Extremely large image generators offer significant transformative potential across diverse sectors. It allows users to design specific prompts to generate realistic images through…