Skip to content

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

Oct 12 · Monday

All papers

Found 6 papers
Filter5

Attack type

Prompt injection3Poisoning and backdoors3Denial of service3

Impact

Unauthorized actions97Data and privacy leaks20Output manipulation41Availability and reliability6Oversight failure4

System type

AI Agent6

Attack surface / entry point

User input3Web pages and interfaces3Documents and messages1Tool and skill descriptions3Distribution channels3

Layer

Application 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 254papers have no tags yet and are not included in filtered results.
Impact：Availability and reliabilityAttack surface / entry point：Web pages and interfacesAttack surface / entry point：Documents and messagesAttack surface / entry point：Tool and skill descriptionsLayer：Application layerClear all

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

  2. Evaluation and benchmarksarXiv 2609.19140

    AgentLSD：在对抗性任务污染下评测 AI 安全 Agent

    评测安全 Agent 在对抗性任务污染下的解题成功与开销

    arXiv
    2609.19140
    Published
    Layer
    Application layer
    Setting
    web agent
    Evaluated models
    Gemma-4 31B, DeepSeek-V4 Flash, GPT-OSS 120B and others6
    AbstractAgentLSD 用配对 web CTF 表明，欺骗性环境证据会改变安全智能体的解题率与工作量。

    AgentLSD 是一个对照框架，用来测量安全智能体在任务本身不变时，对对抗性任务污染的反应。

    Paper analysisRead analysis
  4. 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
You have reached the end