Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
Another 254 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.
提出条件触发的爆炸提示词，并设计摄入期检测器 DeFuse
Published Sep 19
Evaluated models Llama-3.1-8B-Instruct , Llama-3.1-70B-Instruct , Qwen2.5-32B-Instruct and others15 Abstract 论文揭示了条件触发使提示注入绕过防御并在触发时执行工具，提出轻量检测器并在摄入期有效防范。论文针对大语言模型智能体面临的间接提示注入威胁，研究了利用条件句式实现时间分离的爆炸提示词。
提出跨通道分段攻击，利用 MCP 隐式信任外发敏感文件
Published Sep 16
Evaluated models GPT-4o , GPT-4o-mini , GPT-5.4 and others15 Abstract 论文揭示了 MCP 多通道隐式信任层级，通过跨通道分段与协议级利用突破现有防御，展示了严重的凭证外发风险。
提出 TIP，用树搜索为 MCP 响应生成隐蔽注入载荷
Published Mar 25
Evaluated models Qwen2.5-7B-Instruct , Qwen2.5-72B-Instruct , Llama3.1-8B-Instruct and others8 Abstract TIP 在 MCP 工具响应上做黑盒注入。TIP 是面向 MCP 工具响应的 black-box 间接提示注入，目标是在不改工具元数据的情况下生成语义连贯的 JSON 载荷。
Attacks arXiv 2510.09023 · Oct 10, 2025 提出自适应攻击框架，击穿越狱与提示注入防御
Published Oct 10, 2025
Evaluated models Gemini-2.5 Pro , GPT-5 Mini , Llama-3.3 70B and others15 Attacks arXiv 2510.04885 · Oct 6, 2025 提出 RL-Hammer，从零训练攻击模型经工具输出实施提示注入
Published Oct 6, 2025
Evaluated models Llama-3.1-8B-Instruct , Meta-SecAlign-8B , Meta-SecAlign-70B and others10 Abstract 作者称通过无热启动的强化学习可有效突破具备防御的商业模型，论文提出的 RL-Hammer 促使业界关注提示注入风险。RL-Hammer 是一个无需热启动数据、基于 GRPO 算法从零训练的黑盒提示注入对抗攻击框架。现有针对大语言模型智能体的提示注入防御（如 Instruction Hierarchy 与 SecAlign）主要在静态或弱攻击下测试，在面对自动化强力攻击时的真实防御能力缺乏充分检验。方法的核心机制包括。
You have reached the end