Skip to content

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

Oct 12 · Monday

All papers

Found 5 papers
Filter5

Model risks

Dangerous agent actions3

Defense type

Detection and filtering3Instruction–data separation0Permissions and approval2Monitoring and auditing8

Impact

Data and privacy leaks4

System type

Models and APIs16LLM applications8AI Agent25coding agent4web agent3Multi-agent systems1

Layer

Application layer5
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 240papers have no tags yet and are not included in filtered results.
Defense type：Detection and filteringDefense type：Instruction–data separationDefense type：Permissions and approvalSystem type：coding agentSystem type：Multi-agent systemsClear all

Another 240papers do not have category tags yet and are not included in filtered results.

  1. Evaluation and benchmarksarXiv 2610.11773

    研究提出 Agent 安全新维度：识别未履行的安全义务

    提出义务识别基准 ObligationBench，并训练护栏识别 Agent 未履行的安全义务

    arXiv
    2610.11773
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    ObligationGuard, Claude-Opus-4.8, GPT-5.6-Sol and others17
    Abstract义务是护栏缺口。

    作者认为编码智能体的安全不能只靠拦截禁止动作，还要找出终止时仍未做的安全关键动作，并将其称为义务。

    Paper analysisRead analysis
  2. Evaluation and benchmarksarXiv 2609.35557

    论文：容器、权限规则与沙箱都无法区分读取研究代码的是编译器还是编码 Agent

    评测容器、权限规则与沙箱能否区分编译器与编码 Agent 的文件读取

    arXiv
    2609.35557
    Published
    Layer
    Application layer
    Setting
    coding agent
    Abstract此 harness 表达不了编译器可读而智能体不可读，五条路径两边都不覆盖。

    作者在物理流求解器上检查一套编码智能体配置：编译器必须读本组材料与反应模型，这些字节又不得进入模型上下文或离开本机的记录。

    Paper analysisRead analysis
  3. Evaluation and benchmarksarXiv 2605.17380

    Uber proposes ADR enterprise-level agent detection system, deployed on 7,200 hosts for ten months

    提出企业级检测系统 ADR，识别编程 Agent 的提示注入与恶意 MCP

    arXiv
    2605.17380
    Published
    Layer
    Application layer
    Setting
    coding agent

    Abstract提出了端点因果遥测、两级在线分流与离线红队闭环的 ADR 系统，并在生产环境中验证了有效性。

    Paper analysisRead analysis
  4. Evaluation and benchmarksarXiv 2605.14859

    论文提出 AuthBench 基准，评测编码 Agent 能否推断最小权限边界

    提出 AuthBench 评测编码 Agent 最小权限，并验证充足性-紧缩性分解

    arXiv
    2605.14859
    Published
    Layer
    Application layer
    Setting
    coding agent
    Evaluated models
    GPT-5, GPT-5.3-Codex, GPT-5.4 and others9
    Abstract论文提出权限边界推断基准与两阶段分解方法，有效降低安全暴露。

    本文研究代码智能体在执行终端任务前自主推断最小文件权限边界的能力。

    Paper analysisRead analysis
  5. Evaluation and benchmarksarXiv 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