Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 14 papers Another 265 papers do not have category tags yet and are not included in filtered results.
“
About this collection Collection in progress We are building a large AI safety paper collection to help researchers find work related to their interests. Papers are collected automatically andfiltered only for relevance to AI safety , without judging quality, novelty or reading value. The default “Annotated first” shows papers with tags or published paper analyses first. Each group is ordered by original publication date, newest first, with undated papers last. “Newest first” uses publication dates only. This order is not a quality ranking.
One-line summaries, tags and paper analyses are prepared by AI from the papers. Language models may have systematic biases and produce hallucinations.We plan to carry out human annotation and review to reduce errors in this content.
提出 ATLAS 用水平集估计恢复黑盒分类器的对抗输入集合
Published Oct 6
Evaluated models LeNet5 , ResNet50 (CIFAR-10 standard) , ResNet50 (ImageNet standard) and others5 Abstract ATLAS 用主动水平集估计构造黑盒对抗集，作者称其集合比单点攻击更具代表性。ATLAS 是一个查询式 black-box 框架，用来构造诱发失败的对抗输入集合，供鲁棒性审计使用。
提出 SceneJail，利用视频情境上下文越狱视频多模态模型
Published Sep 30
Evaluated models Qwen2.5-VL-7B-Instruct , Qwen2.5-VL-32B-Instruct , Qwen3-VL-8B-Instruct and others8 提出 Repeat-After-Me 自适应视觉提示注入，诱导 VLM 智能体执行指定任务
Published Sep 4
Evaluated models Claude-Opus-4.7 , GPT-5.5 , Gemini-3.1-Pro and others6 Abstract 论文提出了针对黑盒 VLM 的前缀诱导自适应视觉提示注入，在多款模型上诱发了工具调用与隐私泄露。
提出 MAMJ，在元层面交替优化多模态越狱的策略提示与攻击者权重
Published Aug 27
Evaluated models GPT-4o , Gemini-3-Pro-Preview , Seed 2.0 提出 ARENA 音频红队框架，自动构造文本安全且音频接地的越狱输入
Published Aug 16
Evaluated models Audio Flamingo 3 , Qwen2-Audio-7B-Instruct , MiMo-Audio-7B-Instruct and others4 提出 INFER+ 信息过载方法，越狱大型视觉语言模型
Published Jul 3
Evaluated models Qwen3-VL-8B , Qwen2-VL-7B , InternVL3.5-8B and others8 Abstract 用图文过载越狱 LVLM。这篇工作用信息过载 越狱 LVLM，而不是靠 OOD 变换隐藏意图。
提出 ASO，用 GRPO 优化视觉风格以放大越狱攻击
Published Jun 1
Evaluated models GPT-4.1-mini , Gemini-2.5-Flash , Qwen3-VL and others6 Abstract 论文揭示了 MLLM 的风格敏感性脆弱面，提出 ASO 框架利用强化学习优化风格触发器，有效放大了现有视觉越狱效果。
提出 VROP，把有害意图拆成良性视觉 gadget 越狱视觉语言模型
Published Mar 10
Evaluated models GPT-4o , Claude 3.7 Sonnet , GLM-4V-Plus and others7 Abstract VROP 以良性视觉 gadget 与控制流提示词做组合越狱。VROP 是 black-box 多模态越狱框架：不在输入中放显式恶意触发，而把有害目标拆成语义正交的良性视觉 gadget，再用控制流提示词把合成留到后期推理。
提出 FERRET 框架，用扩展生成多轮多模态越狱对话
Published Feb 18
Evaluated models Llama Maverick , Claude Haiku , GPT-4o 提出 MM-Plan 多模态越狱框架，自动规划多轮图像编辑以越狱视觉独占目标
Published Feb 5
Evaluated models Llama-3.2-11B , InternVL3-8B , Qwen3-VL-8B and others8 Abstract 作者称全局规划能攻破对单轮攻击更稳的前沿 MLLM。MM-Plan 是面向 Visual Exclusivity 的 black-box 多模态红队方法，并配有人工基准 VE-Safety。
提出 ReAct 双策略，按反馈改写提示并扰动图像绕过 VLM 安全过滤
Published Jan 30
Evaluated models Gemini-2.0-Flash Attacks arXiv 2511.10692 · Nov 12, 2025 提出 StyleBreak 风格化音频越狱，利用语音属性绕过音频语言模型对齐
Published Nov 12, 2025
Evaluated models Qwen2-Audio-7B-Instruct , MERaLiON-AudioLLM-Whisper-SEA-LION , Ultravox-v0.4.1-Llama-3.1-8B and others6 Attacks arXiv 2508.06837 · Aug 9, 2025 提出 Prometheus，从展示图反推文生图模型的在售提示词
Published Aug 9, 2025
Evaluated models Midjourney , Leonardo.ai , DALL·E and others4 Abstract 训练无关的 proxy 搜索攻击。Prometheus 是针对文生图市场 showcase 的训练无关提示词窃取：攻击者看不到在售文本，只用本地开源 proxy 恢复 subject 和 modifier，并希望换 subject 后风格仍在。
Attacks arXiv 2503.06223 · Mar 8, 2025 提出 RedDiff，用强化扩散生成图像审计 VLM 情境安全失效
Published Mar 8, 2025
Evaluated models LLaVA-1.5-7B , Gemini-1.5-flash , LLaMA-3.2-11B-Vision-Instruct Abstract 用强化扩散生成视觉上下文，审计有害文本情境下的 VLM 安全失效。RedDiffuser 是黑盒审计框架：有害内容不是显式攻击指令，而是固定的部分有毒文本，再配上扩散模型生成的图像，看 VLM 的开放续写会不会变得不安全。
You have reached the end