Skip to content

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

Oct 12 · Monday

All papers

Found 3 papers
Filter3

Attack type

Prompt injection19Poisoning and backdoors4Extraction and theft3Detection evasion0

System type

AI Agent3Multi-agent systems3

Attack surface / entry point

User input80Documents and messages13Tool responses4Tool and skill descriptions5Retrieval corpus3Inter-agent messages3Images, audio and video28Training data10Weights and gradients15Distribution channels3Inference services and hardware10

Layer

Application layer3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 262papers have no tags yet and are not included in filtered results.
Attack type：Extraction and theftAttack type：Detection evasionAttack surface / entry point：Inter-agent messagesClear all

Another 262papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2609.01677

    Skill-as-API：面向智能体软件工程的机密多智能体协作协议

    提出 Skill-as-API，隔离多智能体协作中的 skill 正文与系统提示词

    arXiv
    2609.01677
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems, coding agent
    Abstract协议把 skill 正文留在所有者侧，四层限制发现内容、权限期限和注入拼接。

    Skill-as-API 是面向智能体软件工程的协调协议，用来在跨组织调用时把 skill 的代码和系统提示词留在所有者进程。作者针对三条威胁：经通道或命名空间抽取专有方法，用注入让被调用模型输出系统提示词，以及协作结束后权限继续保留。

    Paper analysisRead analysis
  2. 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
  3. AttacksarXiv 2603.11132

    WebWeaver：以隐蔽的上下文推断攻破 LLM 多智能体系统拓扑机密性

    提出 WebWeaver ，只攻陷单个智能体并从对话上下文恢复多智能体通信拓扑

    arXiv
    2603.11132
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    Llama 3.1 8B, Qwen 2.5 7B, Mistral NeMo 12B and others6
    AbstractWebWeaver 用上下文推断拓扑。

    WebWeaver 是针对 LLM-MAS 通信拓扑机密性的推断攻击：只控制一个任意智能体，从对话上下文恢复全图，而不是查询智能体 ID。

    Paper analysisRead analysis
You have reached the end