Skip to content

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

Oct 13 · Tuesday

All papers

Found 2 papers
Filter5

Attack type

Jailbreaks10Prompt injection19Poisoning and backdoors11Model tampering2Malicious use5

System type

Models and APIs29coding agent0Multi-agent systems2

Attack surface / entry point

User input1Weights and gradients1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 201papers have no tags yet and are not included in filtered results.
Attack type：Model tamperingSystem type：coding agentSystem type：Multi-agent systemsAttack surface / entry point：User inputAttack surface / entry point：Weights and gradientsClear all

Another 201papers do not have category tags yet and are not included in filtered results.

  1. AttacksarXiv 2609.39788

    研究：多智能体系统潜在通信链路可被训练用于提升有害顺从

    提出只训练或篡改多智能体潜在通信链路来提高有害遵从

    arXiv
    2609.39788
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    Llama-3.2-3B-Instruct, Qwen2.5-3B-Instruct, Gemma-3-1B-IT and others7
    Abstract潜在链路本身即可改变冻结智能体系统的安全，奖励既能攻击也能修复。

    学习得到的潜在通信链路会改变由冻结、对齐智能体组成的系统是否遵从有害请求。。作者研究三种拓扑：双智能体、三级顺序协作，以及双专家加汇总。

    Paper analysisRead analysis
You have reached the end