Translation in progress Some entries still include text in the original language.
Oct 12 · Monday
Another 232 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 StegoMemory，评测智能体持久记忆作为跨会话隐写信道
Published Oct 3
Evaluated models Llama 3.1 405B , Claude 3.5 Sonnet , GPT-4o and others13 Abstract 研究揭示智能体持久记忆可作为隐蔽信道跨会话传输机密，写入持久化是主要防御瓶颈，呼吁建立记忆完整性防御。
提出跨独立 Agent 的记忆跳跃攻击，经共享工件在助手间自传播
Published Sep 29
Evaluated models GPT-5.6 Luna , Kimi-K2.6 , GPT-OSS-120B and others6 Abstract 论文证实持久工件与内存可形成跨智能体传播链，揭示了将共享工件纳入安全防线的重要意义。该论文系统研究并量化了通过共享持久工件在具有独立私有内存的 LLM 智能体之间发生自传播的“工件介导传播”攻击风险。
提出 EvoBreak，以良性任务组合诱导自进化 Agent 的持久经验并削弱安全边界
Published Aug 3
Evaluated models GPT-5-mini , Llama-3.1-8B-Instruct 提出 DEEPTRAP 以搜索可诱导不安全轨迹的执行上下文载荷
Published May 11
Evaluated models GPT-5.4 , Claude Sonnet 4.6 , GLM-5 and others9 Abstract DEEPTRAP 用轨迹级搜索发现 OpenClaw 上下文风险，作者称不能只看最终回复。DEEPTRAP 是针对 OpenClaw 的自动化红队框架，搜索执行前被改写的文件、记忆、技能、工具元数据或配置，而不是改用户指令。
构建 Trojan Hippo Bench，评测 Agent 持久记忆投毒与外泄
Published May 4
Evaluated models Gemini 3.1 Pro , GPT-5-mini , GPT-5 Abstract 论文提出了评测智能体持久化记忆攻击与防御的 Trojan Hippo Bench，揭示了潜伏攻击威胁及内存防御的安全与效用权衡。
Proposes LAAF, which automatically attacks LPCI vulnerabilities in agent systems in stages
Published Mar 18
Evaluated models gemini-2.0-flash-001 , claude-3-haiku-20240307 , meta-llama/llama-3.1-70b-instruct and others5 Abstract LAAF does LPCI red teaming with taxonomy plus stage seeding.The authors state that LAAF is an automated red-teaming framework built specifically for LPCI in agentic LLMs. The issue to address is that encoded, delayed, and conditionally triggered payloads can persist in memory or RAG and re-enter across sessions, whereas Garak and PyRIT do not use the previous round's breakthrough results to seed the next stage across the six stages.
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