4 papers
When Harmful Content Gets Camouflaged: Unveiling Perception Failure of LVLMs with CamHarmTI
Yanhui Li, Qi Zhou, Zhihong Xu +3
Large vision-language models (LVLMs) are increasingly used for tasks where detecting multimodal harmful content is crucial, such as online content moderation. However, real-world h…
A Set of Generalized Components to Achieve Effective Poison-only Clean-label Backdoor Attacks with Collaborative Sample Selection and Triggers
Zhixiao Wu, Yao Lu, Jie Wen +3
Poison-only Clean-label Backdoor Attacks aim to covertly inject attacker-desired behavior into DNNs by merely poisoning the dataset without changing the labels. To effectively impl…
Fair-PP: A Synthetic Dataset for Aligning LLM with Personalized Preferences of Social Equity
Qi Zhou, Jie Zhang, Dongxia Wang +5
Human preference plays a crucial role in the refinement of large language models (LLMs). However, collecting human preference feedback is costly and most existing datasets neglect…
Defending LVLMs Against Vision Attacks through Partial-Perception Supervision
Qi Zhou, Tianlin Li, Qing Guo +4
Recent studies have raised significant concerns regarding the vulnerability of Large Vision Language Models (LVLMs) to maliciously injected or perturbed input images, which can mis…