Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 10 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 CRIME 框架，组合良性 Agent 技能诱发恶意行为
Published Oct 5
Evaluated models DeepSeek-V4-Flash , GPT-4o-mini , GPT-4o and others6 Abstract 良性技能经 DCA 或 ACA 组合后可产生恶意环境后果，单独审查对不上。CRIME 把公共技能库中各自通过审查的技能配成两两组合，看联合执行能否实现指定恶意任务。 。
提出 RISE，迭代演化可复用策略对文生图模型做红队
Published Sep 28
Evaluated models DALL·E 3 , Nano Banana 2 , GPT-Image-2 and others7 提出 CRACK，用多智能体辩论在黑盒下越狱文生图多层安全过滤
Published Sep 1
Evaluated models Stable Diffusion v1.4 , SDXL , DALL·E 3 and others4 Abstract CRACK 以分层诊断的多智能体辩论搜索多层 T2I 过滤器的联合规避区域。CRACK 是面向文本生成图像模型多层安全栈的黑盒越狱框架，用几何上的 Detection Surface 解释为何粗粒度反馈不够。
提出 UniAttack 单轮黑盒越狱框架，融合攻击特征绕过多层防御
Published Jun 15
Evaluated models DeepSeek-Chat , DeepSeek-Reasoner , GPT-4.1-Nano and others9 提出 FoodGuardBench 与护栏 FoodGuard-4B，评测并降低食品危害越狱
Published Apr 2
Evaluated models Claude-3.7-Sonnet , GPT-4o , GPT-4.1 and others10 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 提出 MacPrompt 跨语言字符重组越狱，绕过文生图模型的过滤与概念移除
Published Jan 12
Evaluated models SD v2.1 , ESD , SLD (Max) and others14 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。
Attacks arXiv 2503.02174 · Mar 4, 2025 提出 AdvTok 对抗分词攻击，不改文本只改分词来越狱并规避安全分类器
Published Mar 4, 2025
Evaluated models Llama3.2-1B , Llama3.2-3B , Llama3.1-8B and others7 Abstract 作者称非规范分词能躲开对齐并仍得到针对原请求的回复。作者用非规范分词攻击已对齐的子词 LLM：恶意字符串的字符不变，只改 token 边界。
Attacks arXiv 2503.01839 · Mar 4, 2025 提出 PromptTune，微调 LLM 改写提示以越狱文生图护栏
Published Mar 4, 2025
Evaluated models SDXL-Turbo , MACE , SafeGen Abstract LLM 改写可提高过滤器绕过率。PromptTune 用微调 LLM 改写提示词，攻击带安全过滤器或对齐的文生图模型。
You have reached the end