Skip to content

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

Oct 12 · Monday

All papers

Found 4 papers
Filter3

Attack type

Prompt injection4

Defense type

Detection and filtering3

System type

AI Agent4Multi-agent systems4

Attack surface / entry point

User input100Web pages and interfaces12Documents and messages17Tool responses25Tool and skill descriptions15Code repositories and dependencies5Retrieval corpus4Memory writes4Inter-agent messages4Images, audio and video19Training data4Weights and gradients4Distribution channels10

Layer

Application layer4

System component

MCP and skills6Memory4Guardrails and judges3Monitors2Permissions and sandboxing8
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.
Attack surface / entry point：Inter-agent messagesSystem component：Guardrails and judgesSystem component：MonitorsClear all

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

  1. Evaluation and benchmarksarXiv 2609.33102

    ORBIT：基于 UK AISI Inspect 的多智能体安全评测框架

    提出 ORBIT 框架，评测多智能体防御对合谋等威胁的效果

    arXiv
    2609.33102
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Evaluated models
    GPT-5.4, Claude Sonnet 4.6, Qwen3-235B and others5

    AbstractORBIT 用六层配置比较多智能体防御，逐动作监控不迁移到合谋。

    Paper analysisRead analysis
  2. DefensesarXiv 2606.08234

    SciTrace：面向科学发现智能体的轨迹感知安全推理框架

    提出 SciTrace，为科学发现智能体加入跨阶段安全推理与工具轨迹核验

    arXiv
    2606.08234
    Published
    Layer
    Application layer
    Setting
    science agent, Multi-agent systems
    Evaluated models
    Llama-3.1-70B-Instruct, Qwen2.5-72B-Instruct, DeepSeek-V3 and others4
    AbstractSciTrace 把安全推理织入科学智能体各阶段，在 SciSafetyBench 上提高安全指标并保持输出质量。

    SciTrace 是加在科学发现智能体流水线上的安全框架，不是再在各阶段出口放一个独立过滤器。

    Paper analysisRead analysis
  3. DefensesarXiv 2603.04474

    从火花到烈火：建模并缓解基于 LLM 的多智能体协作中的错误级联

    提出谱系图治理层抑制多智能体协作的错误级联

    arXiv
    2603.04474
    Published
    Layer
    Application layer
    Setting
    Multi-agent systems
    Abstract单一种子可沿固定协作图固化为错误共识。

    作者把 LLM-MAS 中“小错变成集体错误共识”做成图上的可测传播，并用只改消息、不改拓扑的插件压低最终感染。

    Paper analysisRead analysis
  4. DefensesarXiv 2505.23559

    SafeScientist：让 LLM 智能体的科学发现具备风险意识

    提出 SafeScientist 四层监控，阻止科研智能体执行高风险或不伦理任务

    arXiv
    2505.23559
    Published
    Layer
    Application layer
    Setting
    science agent, Multi-agent systems
    Evaluated models
    GPT-4o, GPT-4.1, GPT-3.5-turbo and others5
    Abstract四层监控加科研安全基准。

    SafeScientist 是带四层监控的科研智能体框架，并用 SciSafetyBench 评测科学场景中的任务安全。

    Paper analysisRead analysis
You have reached the end