Skip to content

Translation in progress Some entries still include text in the original language.

Oct 12 · Monday

All papers

Found 7 papers
Filter3

Attack type

Prompt injection5Poisoning and backdoors6

Attack technique

Automated search7Encoding and obfuscation3Reasoning-chain manipulation3Defense-targeted7Dormant triggers22

Impact

Unauthorized actions3

System type

AI Agent7

Attack surface / entry point

Documents and messages3Memory writes4

Layer

Application layer7

System component

MCP and skills18Memory6RAG7Guardrails and judges20Monitors1Reasoning chains4Vision9Image generation7Multimodal19
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 261papers have no tags yet and are not included in filtered results.
Attack technique：Automated searchSystem component：MemorySystem component：MonitorsClear all

Another 261papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2609.35576

    研究提出跨 LLM 助手的记忆跳跃攻击

    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

    arXiv
    2609.35576
    Published
    Layer
    Application layer
    Setting
    AI Agent
    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。

    Paper analysisRead analysis
  4. AttacksarXiv 2607.05189

    Researchers propose MemGhost, achieving covert memory injection into persistent personal agents

    提出 MEMGHOST，用单封邮件对持久个人 Agent 做跨会话隐蔽记忆注入

    arXiv
    2607.05189
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-5.4, Claude Sonnet 4.6, Claude Sonnet 4.5 and others6
    Abstract总结了论文的研究背景、双代理优化方法 MEMGHOST、全周期实验结果以及作者对记忆信任边界的启示。

    本文研究了持久化个人智能体面临的隐蔽记忆注入威胁，提出了一套兼顾写入、隐蔽与跨会话生效的自动化生成框架与全周期评测基准。

    Paper analysisRead analysis
  5. AttacksarXiv 2605.15338

    隐藏于记忆：LLM Agent 的潜伏记忆投毒

    提出潜伏记忆投毒，诱导 Agent 把外部文档写成持久伪造记忆

    arXiv
    2605.15338
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-5.4, GPT-5.5, Claude Sonnet 4.6 and others12
    Abstract持久记忆成为跨会话攻击面：通用载荷可写入伪造记忆，并在相关后续任务中影响行为。

    sleeper memory poisoning 研究带持久记忆的 LLM 助手：外部文档能否让助手存下一则伪造的用户记忆，并在原文档消失后的新会话里被取回、用来改变回复或动作。

    Paper analysisRead analysis
  6. AttacksarXiv 2605.11047

    DeepTrap 框架在 OpenClaw 上自动挖掘智能体执行上下文漏洞

    提出 DEEPTRAP 以搜索可诱导不安全轨迹的执行上下文载荷

    arXiv
    2605.11047
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-5.4, Claude Sonnet 4.6, GLM-5 and others9
    AbstractDEEPTRAP 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。

    Paper analysisRead analysis
  7. Evaluation and benchmarksarXiv 2605.01970

    Trojan Hippo Bench: A Dynamic Benchmark for Persistent Memory Attacks and Defenses on LLM Agents

    构建 Trojan Hippo Bench，评测 Agent 持久记忆投毒与外泄

    arXiv
    2605.01970
    Published
    Layer
    Application layer
    Setting
    AI Agent
    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。

    Paper analysisRead analysis
You have reached the end