Skip to content

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

Oct 12 · Monday

All papers

Found 4 papers
Filter5

Impact

Unauthorized actions4

System type

Models and APIs60LLM applications8AI Agent142coding agent31science agent3web agent1Browser and computer use5Multi-agent systems18Embodied systems and robotics3

Layer

Application layer3

System component

Memory2RAG3Guardrails and judges7Monitors3Permissions and sandboxing3Vision18Audio0Multimodal20
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 240papers have no tags yet and are not included in filtered results.
System type：web agentSystem type：Embodied systems and roboticsSystem component：MemorySystem component：MonitorsSystem component：AudioClear all

Another 240papers do not have category tags yet and are not included in filtered results.

  2. OtherarXiv 2610.02662

    论文发现语言驱动机器人安全监控的细化缺口：安全高层计划可能产生不安全执行

    审计机器人安全监控的细化缺口，比较表面计划与图细化轨迹的裁决

    arXiv
    2610.02662
    Published
    Layer
    Application layer
    Setting
    Embodied systems and robotics
    Abstract表面轨迹可漏掉图诱导的禁区进入。

    作者审计 RoboGuard 的一个假设：对高层动作轨迹的安全裁决，在补上语义图诱导的导航和已记录隐式效应之后是否仍然成立。做法是不改验证器，并固定同一条 LTL。

    Paper analysisRead analysis
  4. AttacksarXiv 2604.02623

    论文提出 eTAMP 攻击：网页内容注入可跨会话污染 Web Agent 记忆

    提出 eTAMP，用网页内容跨会话投毒 Web Agent 轨迹记忆并诱导越权操作

    arXiv
    2604.02623
    Published
    Layer
    Application layer
    Setting
    web agent
    Evaluated models
    GPT-5-mini, GPT-5.2, GPT-OSS-120B and others6
    Abstract论文提出了基于环境注入的跨任务记忆投毒攻击 eTAMP，作者报告智能体在环境压力下易感性增加且能力与安全并不协同。

    该论文评估了基于大语言模型的 Web 智能体在利用历史交互轨迹进行记忆增强时的安全脆弱性。

    Paper analysisRead analysis
You have reached the end