arXiv:2607. 26574v2 Announce Type: replace-cross Abstract: Safety classifiers ("guards") are the dominant black-box defense for vision-language models, yet a guard judges an input's surface form, not its meaning: a harmful request re-encoded as set theory, formal logic, a classical language, code, or text rendered inside an image slips past a guard that would block it in plain language - the decode gap.
By Haoyu Zhang, Zhuoxi Wang, Shibo Zheng, Yi Feng, Xiao Luo, Zijian Xiao, Haowen Xu, Xiangchen Guan, Mohammad Zandsalimy, Shanu Sushmita
arXiv:2608. 01043v2 Announce Type: replace-cross Abstract: We report a counter-intuitive interaction between image inputs and existing black-box defenses on Vision--Language Models (VLMs): pairing an encoded jailbreak prompt with an unrelated decoy image can sharply lower attack success rate (ASR).
By Haoyu Zhang, Xiangchen Guan, Shibo Zheng, Mohammad Zandsalimy, Shanu Sushmita
arXiv:2606. 03647v1 Announce Type: cross Abstract: Accurately evaluating adversarial robustness is a longstanding challenge.
By Vincent Limbach, Jonas Dornbusch, David L\"udke, Stephan G\"unnemann, Leo Schwinn
arXiv:2604. 06247v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) and Vision-Language Models (VLMs) are vulnerable to jailbreaks and prompt injections delivered through text or images.
By Guy Azov, Ofer Rivlin, Guy Shtar
arXiv:2607. 26639v1 Announce Type: cross Abstract: A self-check defense asks the target model to assess a request before answering it; SAGE, the strongest published instance, reports an average 99% defense success rate.
By Haoyu Zhang, Shibo Zheng, Xiangchen Guan, Zhuoxi Wang, Zijian Xiao, Mohammad Zandsalimy, Shanu Sushmita
arXiv:2508. 10029v3 Announce Type: replace-cross Abstract: Safety-aligned large language models can still be manipulated through white-box interventions that modify their internal representations.
By Wenpeng Xing, Bohan Yang, Mohan Li, Chunqiang Hu, Haitao Xu, Ningyu Zhang, Bo Lin, Meng Han
A self-check defense asks the target model to assess a request before answering it; SAGE, the strongest published instance, reports an average 99% defense success rate. We show it can be breached by composing two attacks that are individually harmless against it: an established code-completion encoding and an established best-of-N search, neither of which exceeds 4.
arXiv:2605. 10764v3 Announce Type: replace-cross Abstract: Recent studies show that gradient-based universal image jailbreaks on vision-language models (VLMs) exhibit little or no cross-model transferability, casting doubt on the feasibility of transferable multimodal jailbreaks.
By Mengqi He, Xinyu Tian, Xin Shen, Shu Zou, Jinhong Ni, Zhaoyuan Yang, Weikang Li, Xuesong Li, Jing Zhang
arXiv:2604. 12616v2 Announce Type: replace Abstract: Vision-Language Models (VLMs) expand the attack surface of safety-aligned systems by coupling visual perception with text generation.
By Jianhao Chen, Haoyang Chen, Hanjie Zhao, Haozhe Liang, Zheng Wang, Tieyun Qian
arXiv:2608. 14392v1 Announce Type: new Abstract: Neuron- and path-level interventions offer the finest-grained route to defending large language models (LLMs) against jailbreak attacks, yet existing methods fall short of this promise, i.
By Wei Zhao, Zhe Li, Peixin Zhang, Jun Sun
arXiv:2606. 04027v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) generate text by iteratively denoising partially masked sequences under bidirectional context, exposing a safety surface distinct from autoregressive LLMs.
By Yingzi Ma, Zhengyue Zhao, Xiaogeng Liu, Minhui Xue, Yue Zhao, Chaowei Xiao
arXiv:2510. 02999v5 Announce Type: replace-cross Abstract: Existing gradient-based jailbreak attacks on Large Language Models (LLMs) typically optimize adversarial suffixes to align the LLM output with predefined target responses.
By Xinzhe Huang, Wenjing Hu, Tianhang Zheng, Kedong Xiu, Hongsheng Hu, Xiaojun Jia, Di Wang, Zhan Qin, Kui Ren