Skip to content

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

Oct 12 · Monday

All papers

Found 3 papers
Filter5

Attack type

Prompt injection3Poisoning and backdoors3

Defense type

Instruction–data separation3Monitoring and auditing5

Impact

Unauthorized actions3

System type

AI Agent3

Attack surface / entry point

Web pages and interfaces3Documents and messages3Tool responses4Tool and skill descriptions3Memory writes5Distribution channels3

Layer

Application layer3

System component

MCP and skills3Memory3Monitors0Permissions and sandboxing6Embeddings0
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 254papers have no tags yet and are not included in filtered results.
Defense type：Instruction–data separationAttack surface / entry point：Documents and messagesSystem component：MemorySystem component：MonitorsSystem component：EmbeddingsClear all

Another 254papers do not have category tags yet and are not included in filtered results.

  2. DefensesarXiv 2606.24322

    Protecting LLM agent long-term memory from poisoning: tamper-evident, source-bound permissions and machine-checkable guarantees

    提出 TMA-NM，以写时来源绑定抵御 Agent 长期记忆投毒

    arXiv
    2606.24322
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    gpt-5-chat, gpt-4o-mini, claude-opus-4.1 and others8
    AbstractTMA-NM 用来源绑定的行动权限挡住记忆洗白。

    TMA-NM 把 LLM 智能体长期记忆的行动权限绑到写时来源，用来挡住跨会话记忆投毒。

    Paper analysisRead analysis
  3. DefensesarXiv 2603.12644

    揭示自主 Agent 的安全威胁与防御架构：OpenClaw 案例研究

    梳理自主 Agent 威胁并提出全生命周期防御蓝图 FASA

    arXiv
    2603.12644
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Abstract以 OpenClaw 为例划分三层风险，并用 FASA 描述从输入到系统执行的防御。

    这是一份以 OpenClaw 为案例的威胁梳理和防御架构报告，不是带分数的攻击或防御评测。

    Paper analysisRead analysis
You have reached the end