Skip to content

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

Oct 13 · Tuesday

Agent safety · Papers

Found 1 paper
Filter1

Layer

Model layer1Application layer140
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
Layer：Model layerTopic: Agent safetyClear all
  1. Evaluation and benchmarksarXiv 2609.35408

    研究揭示 LLM 交付物修订痕迹导致的无意泄露，并提出 RevLeakBench 基准

    用 RevLeakBench 测量 LLM 交付物修订痕迹的无意泄露

    arXiv
    2609.35408
    Published
    Layer
    Model layer
    Setting
    AI Agent
    Evaluated models
    GPT-5.6, GPT-5.5, DeepSeek-V4-Pro and others6
    Abstract修订痕迹让撤回项重新进入交付物。

    修订痕迹指模型按要求删掉或换掉一项后，又在交代这次修改时把它写进给第三方的交付物。

    Paper analysisRead analysis
You have reached the end