4 papers
HoloFair: Unified T2I Fairness Evaluation and Fair-GRPO Debiasing
Ruyi Chen, Lu Zhou, Xiaogang Xu +3
Text-to-Image (T2I) models have made significant strides in visual realism and semantic consistency, yet they often perpetuate and amplify societal biases. Existing evaluation meth…
LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments
Chiyu Zhang, Huiqin Yang, Bendong Jiang +8
The rapid proliferation of LLM-based autonomous agents in real operating system environments introduces a new category of safety risk beyond content safety: behavior jailbreak, whe…
Jailbreaking Commercial Black-Box LLMs with Explicitly Harmful Prompts
Chiyu Zhang, Lu Zhou, Xiaogang Xu +3
Existing black-box jailbreak attacks achieve certain success on non-reasoning models but degrade significantly on recent SOTA reasoning models. To improve attack ability, inspired…
Adversarial Attacks of Vision Tasks in the Past 10 Years: A Survey
Chiyu Zhang, Lu Zhou, Xiaogang Xu +2
With the advent of Large Vision-Language Models (LVLMs), new attack vectors, such as cognitive bias, prompt injection, and jailbreaking, have emerged. Understanding these attacks p…