Skip to content

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

Oct 12 · Monday

All papers

Found 3 papers
Filter4

Impact

Harmful content3Unauthorized actions11Data and privacy leaks9Output manipulation11Oversight failure16

System component

Memory0Guardrails and judges17Monitors3Fine-tuning and open weights3Vision4Audio3Image generation4Embeddings0Multimodal10
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.
Impact：Harmful contentSystem component：MemorySystem component：MonitorsSystem component：EmbeddingsClear 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
  2. Evaluation and benchmarksarXiv 2609.05797

    Paper finds safety monitors mainly block requests the model would already refuse

    评估安全监视器并提出双侧梯级微调以减少会答有害请求的漏检

    arXiv
    2609.05797
    Published
    Layer
    Prompt layer
    Setting
    Models and APIs
    Evaluated models
    Gemma-4-31B-IT, Qwen3-32B, Llama Guard 3 8B and others6

    Abstract论文发现安全监视器大多拦截模型已拒答请求，指出明确度偏差是共性原因，并通过双侧梯级微调提升回答请求的召回表现。

    Paper analysisRead analysis
  3. 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