Skip to content

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

Oct 12 · Monday

All papers

Found 3 papers
Filter6

Attack type

Prompt injection3

Defense type

Detection and filtering2Instruction–data separation1Permissions and approval1

System type

LLM applications5AI Agent20coding agent1Multi-agent systems2

Attack surface / entry point

User input7Documents and messages3Tool responses4Tool and skill descriptions8Memory writes3Inter-agent messages8Distribution channels6

Layer

Application layer3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 247papers have no tags yet and are not included in filtered results.
Defense type：Detection and filteringDefense type：Instruction–data separationDefense type：Permissions and approvalSystem type：coding agentSystem type：Multi-agent systemsAttack surface / entry point：Documents and messagesClear all

Another 247papers do not have category tags yet and are not included in filtered results.

  2. DefensesarXiv 2605.17380

    Uber proposes ADR enterprise-level agent detection system, deployed on 7,200 hosts for ten months

    提出企业级检测系统 ADR，识别编程 Agent 的提示注入与恶意 MCP

    arXiv
    2605.17380
    Published
    Layer
    Application layer
    Setting
    coding agent

    Abstract提出了端点因果遥测、两级在线分流与离线红队闭环的 ADR 系统，并在生产环境中验证了有效性。

    Paper analysisRead analysis
  3. DefensesarXiv 2603.04474

    从火花到烈火：建模并缓解基于 LLM 的多智能体协作中的错误级联

    提出谱系图治理层抑制多智能体协作的错误级联

    arXiv
    2603.04474
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Abstract单一种子可沿固定协作图固化为错误共识。

    作者把 LLM-MAS 中“小错变成集体错误共识”做成图上的可测传播，并用只改消息、不改拓扑的插件压低最终感染。

    Paper analysisRead analysis
You have reached the end