Skip to content

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

Oct 13 · Tuesday

All papers

Found 1 paper
Filter4

System type

Models and APIs0LLM applications3AI Agent21coding agent0web agent9Multi-agent systems1

Attack surface / entry point

User input161Web pages and interfaces1Tool responses6Tool and skill descriptions15Code repositories and dependencies11Memory writes3Inter-agent messages8Images, audio and video66Training data24Weights and gradients46Distribution channels27Inference services and hardware12
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 213papers have no tags yet and are not included in filtered results.
System type：Models and APIsSystem type：coding agentSystem type：Multi-agent systemsAttack surface / entry point：Web pages and interfacesClear all

Another 213papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2608.00718

    研究揭示多智能体 LLM 流水线的结构性漏洞

    提出多智能体流水线的边界攻击，使对抗内容作为可信输入跨层传播

    arXiv
    2608.00718
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    GPT-5-mini, Claude Sonnet 4.5, Kimi K2.5
    Abstract缺边界校验使对抗内容跨智能体传播，作者称这是架构属性而非模型能力。

    作者把多智能体 LLM 流水线的对抗问题定义为缺少边界校验，并用生产轨迹和受控实验检查脆弱性来自架构还是骨干模型。中间输出未经验证就传给下游。作者认为，一旦某级接受对抗内容，后续智能体会把它当作可信输入。

    Paper analysisRead analysis
You have reached the end