Skip to content

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

Oct 13 · Tuesday

All papers

Found 1 paper
Filter3

Attack type

Prompt injection33Poisoning and backdoors37Extraction and theft1Malicious use0

Attack surface / entry point

User input73Code repositories and dependencies3Retrieval corpus3Memory writes1Inter-agent messages4Images, audio and video12Training data8Weights and gradients11Inference services and hardware9
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.
Attack type：Extraction and theftAttack type：Malicious useAttack surface / entry point：Memory writesClear all

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

  1. Evaluation and benchmarksarXiv 2608.03272

    多智能体协同过滤系统的连接性攻击与防御研究

    复现 AgentCF 上的多智能体攻防并刻画连通性作用

    arXiv
    2608.03272
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    Qwen3-235B-A22B, Claude Haiku 4.5, Mixtral 8×7B and others4
    Abstract连通性沿 k 与ρ改变攻防，且用户/物品与早期/稳态需要分开看。

    作者在 AgentCF 上研究连通性如何改变多智能体协同过滤的攻防，复现已有方法而不是提出新载荷。

    Paper analysisRead analysis
You have reached the end