Skip to content

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

Oct 13 · Tuesday

All papers

Found 2 papers
Filter3

Layer

Model layer2Application layer4

System component

Guardrails and judges4Monitors1Reasoning chains10Vision1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 215papers have no tags yet and are not included in filtered results.
Layer：Model layerSystem component：MonitorsSystem component：VisionClear all

Another 215papers do not have category tags yet and are not included in filtered results.

  1. Analysis and theoryarXiv 2610.09517

    审计发现 CLIP 安全分数主要反映画面与提示词场景的相似度

    开环审计冻结视觉语言安全分，发现其反映场景模板而非危险感知

    arXiv
    2610.09517
    Published
    Layer
    Model layer
    Setting
    Embodied systems and robotics
    Evaluated models
    CLIP ViT-B/32, CLIP ViT-L/14, Qwen2-VL-7B
    Abstract论文审计了冻结 VLM 安全评分机制，指出其反映场景模板而非危险感知，为安全强化学习评估提供了严谨基准。

    本文是一项针对安全强化学习中冻结视觉语言模型（VLM）安全评分机制的实证审计研究。

    Paper analysisRead analysis
  2. Analysis and theoryarXiv 2609.37312

    研究：隐蔽推理必然留下信息痕迹，但思维链未必可读

    分析隐蔽推理在思维链监控下的信息足迹下界与不可读性

    arXiv
    2609.37312
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    Qwen2.5-7B-Instruct, Llama-3.1-8B-Instruct, Qwen 3.5 397B-A17B and others12

    Abstract论文从理论与实证探明了思维链监控的边界：复杂隐蔽计算必然泄露信息足迹且需承担长度税，但该足迹可被在线加密而不可读。

    Paper analysisRead analysis
You have reached the end