Skip to content

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

Oct 13 · Tuesday

All papers

Found 2 papers
Filter4

Defense type

Detection and filtering2Instruction–data separation3Monitoring and auditing6

Attack surface / entry point

Documents and messages2Tool responses4

System component

Memory1Guardrails and judges6Monitors1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 215papers have no tags yet and are not included in filtered results.
Defense type：Detection and filteringAttack surface / entry point：Documents and messagesSystem component：MemorySystem component：MonitorsClear all

Another 215papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2607.06595

    When Agents Remember Too Much: Memory Poisoning Attacks against Large Language Model Agents

    Proposed GhostWriter memory poisoning, which writes into the agent's long-term memory via email and calendar and activates across sessions

    arXiv
    2607.06595
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-5.4-mini, DeepSeek-V4-Flash, Gemini-2.5-Flash and others4
    Paper analysisRead analysis
  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
You have reached the end