Skip to content

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

Oct 12 · Monday

Agent safety · Papers

Found 2 papers
Filter3

System type

AI Agent33Multi-agent systems2

Attack surface / entry point

Documents and messages1Tool responses2Memory writes4Inter-agent messages7
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
System type：Multi-agent systemsAttack surface / entry point：Documents and messagesAttack surface / entry point：Tool responsesTopic: Agent safetyClear all
  1. DefensesarXiv 2610.07657

    DEFER1 多智能体防御研究报告受控测试中的攻击成功率下降

    实现 DEFER，以确定性检查优先拦截多智能体流水线的内容攻击

    arXiv
    2610.07657
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    Qwen3-235B-A22B-Instruct-2507, gpt-oss-120b, Llama-4-Scout-17B-16E-Instruct and others5
    AbstractDEFER 把确定性检查放在 judge 之前。

    DEFER 用来测量多智能体授权流水线里，确定性规则在何处结束、LLM judge 从何处开始。

    Paper analysisRead analysis
You have reached the end