Skip to content

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

Oct 13 · Tuesday

All papers

Found 5 papers
Filter4

Attack type

Prompt injection5Poisoning and backdoors5Denial of service6

Impact

Unauthorized actions46Data and privacy leaks12Output manipulation48Availability and reliability5

System type

AI Agent4

Attack surface / entry point

Tool and skill descriptions3Distribution channels3

Layer

Model layer0Application layer5Training and data layer6

System component

MCP and skills3
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.
Attack type：Poisoning and backdoorsImpact：Availability and reliabilityLayer：Model layerLayer：Application layerClear all

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

  3. AttacksarXiv 2608.12273

    研究者提出 Convergent Detour Hijacking 攻击，可让技能型 LLM Agent 绕路并放大资源消耗

    提出 CDH 攻击，让技能型 Agent 绕路放大资源消耗

    arXiv
    2608.12273
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Claude-Haiku-4.5, DeepSeek-V4-Pro, DeepSeek-V4-Flash and others6
    AbstractCDH 让静态技能在保持任务完成时拉高调用与 token，耗时则因后端而异。

    CDH 是针对渐进披露技能智能体的发布者侧、纯文本攻击：一个静态协调器把本可正确完成的任务，拐进有界但更耗资源的技能绕路，再交还原任务。

    Paper analysisRead analysis
  4. AttacksarXiv 2603.03919

    When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking Attacks in RAG

    提出 TabooRAG，用单篇文档迁移阻断 RAG 对良性查询的回答

    arXiv
    2603.03919
    Published
    Layer
    Application layer
    Setting
    LLM applications
    Evaluated models
    Llama-3-8B-Instruct, Ministral-3-8B-Instruct-2512, Gemma-3-12B-it and others9
    AbstractTabooRAG 用代理侧风险文档迁移阻断 RAG。

    TabooRAG 是面向 RAG 可用性的可迁移阻断攻击，不改已有文档，也不读取目标反馈。

    Paper analysisRead analysis
You have reached the end