Skip to content

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

Oct 12 · Monday

All papers

Found 5 papers
Filter3

Attack type

Prompt injection3

Defense type

Permissions and approval3

Impact

Unauthorized actions5Data and privacy leaks4

System type

AI Agent57coding agent5Multi-agent systems5

Layer

Application layer5

System component

Memory3Permissions and sandboxing5
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 265papers have no tags yet and are not included in filtered results.
Impact：Unauthorized actionsSystem type：Multi-agent systemsSystem component：Permissions and sandboxingClear all

Another 265papers do not have category tags yet and are not included in filtered results.

  2. DefensesarXiv 2609.17648

    多智能体 LLM 流水线中的信任传播与结构隔离

    用任务绑定令牌和策略预言机拦住多智能体流水线的未授权执行

    arXiv
    2609.17648
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    gemma4:31b-cloud
    Abstract结构性授权拦住了记忆投毒的未授权执行，持密钥时承重的是策略预言机。

    作者在一条会改写沙箱邮件库的四智能体流水线上，检查低权限失陷会不会变成未授权的真实动作。

    Paper analysisRead analysis
  3. DefensesarXiv 2609.15803

    研究者提出 k-robust 联盟对齐，用多智能体评审委托授权

    提出 k-robust 联盟对齐，刻画误对齐评审下的安全委托授权

    arXiv
    2609.15803
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Abstract联盟覆盖使无个体对齐的评审面板仍可相对基线安全授权，数值分数改善完备性。

    委托授权的安全不要求每位评审者对齐，而要求面板在效用空间覆盖委托人。

    Paper analysisRead analysis
  4. Evaluation and benchmarksarXiv 2608.07556

    MasDrift：跨多智能体架构的授权保持基准

    提出 MasDrift，评测多智能体在良性任务中的授权保持

    arXiv
    2608.07556
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    DeepSeek V4 Flash, Qwen3.7 Plus, GPT-5.4 Nano and others6
    Abstract授权保持可被测量：层级用未授权动作换完成率，重锚定比沿链携带更稳。

    MasDrift 把多智能体设计中的授权保持做成可测量性质，对象是没有攻击者的普通委托。

    Paper analysisRead analysis
  5. AttacksarXiv 2605.08460

    论文建模多智能体网络中的子智能体继承攻击面

    建模并利用多智能体网络中子智能体生成时的记忆继承漏洞

    arXiv
    2605.08460
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    MiniMax M2.5, Llama-4-Maverick-17B-128E-Instruct-FP8, Qwen3.5-Plus and others5
    Abstract形式化子智能体继承，在 OpenClaw 上演示四类编排层漏洞并提出防御。

    作者对多智能体网络里的子智能体继承做形式化分析，并用开源框架上的 PoC 演示编排层如何让单点妥协继续扩散。

    Paper analysisRead analysis
You have reached the end