Skip to content

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

Oct 12 · Monday

All papers

Found 9 papers
Filter5

Attack type

Jailbreaks9Prompt injection64Poisoning and backdoors17Detection evasion3Malicious use6

Defense type

Permissions and approval5Monitoring and auditing4

Impact

Unauthorized actions5

System type

Models and APIs7AI Agent9Multi-agent systems1

Attack surface / entry point

User input9Tool responses3

Layer

Application layer9

System component

Memory3Guardrails and judges10Monitors4Permissions and sandboxing5
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 232papers have no tags yet and are not included in filtered results.
Attack type：JailbreaksSystem type：AI AgentSystem type：Multi-agent systemsSystem component：MonitorsSystem component：Permissions and sandboxingClear all

Another 232papers do not have category tags yet and are not included in filtered results.

  1. Evaluation and benchmarksarXiv 2610.07089

    研究者提出统一滥用监控基准，覆盖分解攻击与提示注入约 6200 条轨迹

    提出危害窗口与区间指标，统一评测分解攻击和提示注入下的智能体滥用监视

    arXiv
    2610.07089
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Gemma 4 26B-A4B, Qwen3.6 27B, Qwen3.5 27B and others12

    Abstract统一智能体滥用监视框架，动作视角兼顾两类威胁但危害定位仍存瓶颈。

    Paper analysisRead analysis
  3. DefensesarXiv 2609.34518

    SEAD 论文提出工具型 Agent 的状态视角攻击与防御方法 DART 与 SAGE

    提出工具型 Agent 的自适应攻击 DART 与预执行防御 SAGE

    arXiv
    2609.34518
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    GPT-5.6 Luna, GPT-5.6 Terra, Gemini 3.8 Flash and others5

    Abstract论文提出状态控制框架 SEAD、攻击 DART 与防御 SAGE，实验显示执行反馈与环境探测在攻防交互中具有关键作用。

    Paper analysisRead analysis
  4. DefensesarXiv 2609.28693

    skilder：以角色化技能包为工具型 LLM 智能体做访问控制

    提出 Skilder，按角色渐进下发企业工具并确定性拦截越权调用

    arXiv
    2609.28693
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    Claude Haiku 4.5, Qwen 3.5 122B, Gemma 4 31B and others6
    AbstractSkilder 用单 MCP 服务器按角色交付工具并硬拦截。

    Skilder 把企业工具型智能体的能力按角色打包，经一个 MCP 服务器做渐进发现，使工具范围由服务器而不是提示词来执行。

    Paper analysisRead analysis
  6. DefensesarXiv 2609.14003

    FlowSeal：用信息流控制阻断 LLM Agent 的隐私泄露

    提出 FLOWSEAL，用工具级信息流控制阻断智能体隐私泄露

    arXiv
    2609.14003
    Published
    Layer
    Application layer
    Setting
    AI Agent
    Evaluated models
    DeepSeek-V3.2, GPT-4.1-mini, Gemini-Flash-2.5

    Abstract作者分析大模型智能体隐私检查与攻击面重合问题，提出外部拦截防御 FLOWSEAL 并验证有效性。

    Paper analysisRead analysis
  9. 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