Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
All papers Found 15 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.
Proposing an option channel attack that renames option labels so that agent guardrails allow prohibited operations
Published Oct 9
Evaluated models LAYA-TD , LAYA-EN , LAYA-ML and others5 Abstract The authors' evaluation indicates that typed models should not serve as final safety arbiters; they are susceptible to off-policy text and option name manipulation, and confidence filtering cannot resist attacks.
提出 ASPIRE 行为图搜索，开放式发现 Agent 提示注入漏洞
Published Oct 7
Evaluated models Gemini-3.7-Flash , DeepSeek-V4-Flash , Gemini-2.5-flash Abstract ASPIRE 把提示注入红队从载荷优化改成行为图引导的开放式漏洞发现。ASPIRE 是给搭建方用的智能体提示注入红队引擎，目标是开放式画出可利用的行为路径，而不是在固定任务上打磨一条载荷。
提出 AdaLCPI，把恶意指令拆成碎片嵌入工具返回并诱导 Agent 越权执行
Published Sep 29
Evaluated models GPT-4.1 , GPT-5.1 , GPT-5.6-Luna and others7 用跨目标课程强化学习训练提示注入红队，攻破前沿智能体
Published Sep 27
Evaluated models GPT-4o-mini , GPT-5-nano , GPT-5.6-Luna and others12 Abstract 提出跨目标模型课程强化学习，攻破前沿模型冷启动瓶颈并实现跨模型迁移。该研究针对强化学习自动化提示注入红队在攻击前沿大模型时的冷启动问题，提出了一种基于目标模型鲁棒性递进的课程强化学习方法。
提出 AgentXploit，从代码仓库发现攻击路径并在运行时验证利用
Published Sep 25
Evaluated models GPT-4.1 提出 Search Harness，把间接提示注入做成测试时搜索并自适应利用
Published Sep 4
Evaluated models Claude Opus 4.8 , GPT-5.5 提出 ECLIPSE 双通道提示注入，劫持长程 Agent 的动作轨迹
Published Aug 31
Evaluated models DeepSeek , GPT-4o , Claude 4.8 Opus and others7 系统分析智能体支付协议的前置上下文操纵与授权威胁
Published Aug 25 提出 PIMiner，用可复用策略库自动搜索并迁移针对智能体的提示注入
Published Aug 6
Evaluated models Gemini-2.5-Pro , DeepSeek-V4-Pro , GPT-4o-mini and others10 提出 AHA 自动科研循环，发现生产 Agent 的可复用漏洞概念
Published Jul 13
Evaluated models Minimax-M2.7 , Kimi-K2.6 , Deepseek-V4-Pro and others5 Abstract 论文提出基于可证伪科研循环的 AHA 框架，从生产级智能体中挖掘并沉淀漏洞概念图，提升攻击复用率并指导防御加固。AHA 是一项针对生产级 LLM 智能体自动化红队测试的研究，旨在解决传统方法仅保留具体攻击载荷而缺乏成因解释、导致跨版本复用困难且无法指导修复的问题。
提出 Relink 攻击，在 Agent 压缩边界将分散良性片段重组为恶意指令
Published Jun 20
Evaluated models Gemma-4-31B-it , GPT-OSS-20B , Qwen3.6-27B and others15 Abstract 论文指出提示词压缩引入重链漏洞，提出 RELINK 攻击工具与 KBRA 边界审计防御，证明压缩边界应作为关键安全边界。本文研究了智能体基于摘要的提示词压缩所引入的新型安全漏洞——重链（Relinking），并提出了系统化的攻击构建方法与边界审计防御机制。
提出 MAStrike，用 Shapley 选联盟对多智能体做共谋红队
Published Jun 11
Evaluated models Claude Opus 4.7 , GPT-5.5 , Gemini 3.1 Pro 提出 AdapTools 自适应间接提示注入，诱导智能体调用指定工具
Published Feb 24
Evaluated models GPT-4.1 , DeepSeek-R1 , Gemini-2.5-Flash and others6 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。
Attacks arXiv 2507.10457 · Jul 15, 2025 提出 LPCI，把延迟条件载荷写入记忆与检索库以跨会话触发
Published Jul 15, 2025
Evaluated models ChatGPT , Claude , LLaMA3 and others8 Abstract 作者定义 LPCI。作者把LPCI 定义为针对智能体逻辑执行、记忆留存和工具集成的跨阶段漏洞类，而不是单次输入上的提示改写。
You have reached the end