Translation in progress Some entries still include text in the original language.
Oct 13 · Tuesday
All papers Found 12 papers Another 215 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.
Retest and extend prompt injection against AI agents, and use Agent Card deception to manipulate A2A selection
Published Oct 8
Evaluated models Ollama Mistral 0.9.5 , llama3-8b-8192 , gemini-2.0-flash-lite and others5 Abstract Single-agent filtering and classification can be bypassed by format or wording, and A2A card selection is also biased toward names and descriptions.The authors retested prompt injection on their own LangChain, AutoGen, and A2A systems, and modified the Agent Card to see if choices shifted. The abstract states the experiments mainly highlight single-agent weaknesses while extending attacks to multi-agent.
提出 PERSISTBD，发布前强化供应链后门使其经良性 SFT 与 RL 后仍外发凭据
Published Oct 6
Evaluated models Qwen2.5-Coder-3B-Instruct , Qwen2.5-Coder-7B-Instruct , Qwen3-Coder-30B-A3B-Instruct Abstract 总结了论文关于后门在 SFT/RL 中存活的发现、两因子机制、PERSISTBD 方法与核心数字。本文研究第三方 LLM 智能体在开发者进行良性监督微调（SFT）和强化学习（RL）后训练时的后门持久性风险。
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 MemLeak，评估多租户 Agent 共享向量记忆的跨用户泄露
Published Oct 3
Evaluated models Gemini 2.5 Flash , Claude Sonnet 4.5 , all-MiniLM-L6-v2 and others5 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 PMPA，经外部源向 Agent 持久记忆投毒并跨会话泄露隐私
Published Sep 12
Evaluated models DeepSeek-V4-Flash , DeepSeek-V4-Pro , Qwen3-Max Abstract 论文提出了持久记忆投毒攻击 PMPA，报告了 harness 智能体在处理外部数据时易受跨会话记忆投毒与隐私泄露的风险。
提出 EVOMAL，诱导自演化编码 Agent 在创建技能时自我投毒并蠕虫传播
Published Aug 26
Evaluated models Devstral-Small-2 , Gemma-4-31B-IT , Qwen3-Coder-Next and others7 Abstract 论文指出了自演化智能体模仿检索代码的自我毒化漏洞，提出 EVOMAL 攻击与防御，阐明了供应链新风险。
提出 ElasticBack，在单个 Agent 技能中植入条件后门
Published Aug 10
Evaluated models GLM-5.2 , MiniMax-M3 , GPT-5.4 and others4 Abstract ElasticBack 用冻结规则加遗传搜索演化 trigger，在单 skill 上做条件后门。ElasticBack 是放在 LLM agent 单个 skill 里的条件后门攻击。 。
提出 PoisonedEvolution 轨迹投毒，诱导自演化技能系统固化恶意行为
Published Aug 6
Evaluated models GPT-5.4 , MiniMax-M2.5 , DeepSeek-V3.2 and others6 Abstract 论文揭示自演化技能系统的证据晋升漏洞，提出并验证轨迹投毒攻击。这篇论文揭示了自演化技能系统在将交互经验转化为持久指令时的安全风险。
提出 CFD 跨会话分解攻击，利用工件来源缺口绕过工具型 Agent 的本地检查
Published Jun 8
Evaluated models GPT-4.1 , GPT-5-nano , Claude-3.5-Sonnet and others6 Abstract CFD 用无指令 artifact 把越狱拆到跨会话。CFD 针对工具型 LLM 智能体：利用 artifact 来源不被跟踪这一部署失败模式，把有害目标拆开后延迟组合。
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。
Propose WebWeaver, which compromises only a single agent and recovers the multi-agent communication topology from conversation context.
Published Mar 12
Evaluated models Llama 3.1 8B , Qwen 2.5 7B , Mistral NeMo 12B and others6 Abstract WebWeaver infers topology from context.WebWeaver is an inference attack against the confidentiality of LLM-MAS communication topology: it controls only one arbitrary agent and recovers the full graph from dialogue context, rather than querying agent IDs.
You have reached the end