3 papers
cs.CL2025
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…
cs.CV2025
Improving Adversarial Transferability on Vision Transformers via Forward Propagation Refinement
Yuchen Ren, Zhengyu Zhao, Chenhao Lin +4
Vision Transformers (ViTs) have been widely applied in various computer vision and vision-language tasks. To gain insights into their robustness in practical scenarios, transferabl…
cs.CR2024
Improving Integrated Gradient-based Transferable Adversarial Examples by Refining the Integration Path
Yuchen Ren, Zhengyu Zhao, Chenhao Lin +4
Transferable adversarial examples are known to cause threats in practical, black-box attack scenarios. A notable approach to improving transferability is using integrated gradients…