Skip to content

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

Oct 13 · Tuesday

Defenses and guardrails · Papers

Found 3 papers
Filter3

Attack type

Jailbreaks3

Defense type

Monitoring and auditing3

System type

AI Agent3

Attack surface / entry point

User input3

Layer

Model layer7Application layer3

System component

RAG0Guardrails and judges6Monitors3
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
Layer：Application layerSystem component：RAGSystem component：MonitorsTopic: Defenses and guardrailsClear all
  3. 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