Skip to content

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

Oct 12 · Monday

All papers

Found 2 papers
Filter4

Attack type

Extraction and theft2Detection evasion0

Layer

Model layer1Training and data layer3Infrastructure layer1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 233papers have no tags yet and are not included in filtered results.
Attack type：Extraction and theftAttack type：Detection evasionLayer：Model layerLayer：Infrastructure layerClear all

Another 233papers do not have category tags yet and are not included in filtered results.

  1. Analysis and theoryarXiv 2610.02504

    HXAI：分布式能源系统中的分层隐私保护可解释 AI 框架

    提出 HXAI 分层隐私解释框架，本地保留细解释并只发布加噪摘要

    arXiv
    2610.02504
    Published
    Layer
    Infrastructure layer
    Setting
    Models and APIs
    Evaluated models
    gradient-boosted tree regression models
    AbstractHXAI 把无噪声局部 SHAP 留在家庭内，只聚合差分隐私摘要。

    HXAI 是面向分布式能源系统的分层隐私保护解释框架，服务规划、监测与诊断，而不是实时控制。

    Paper analysisRead analysis
  2. Analysis and theoryarXiv 2601.02002

    Exploring Methods to Detect Recommender System Data Memorization in Large Language Models

    比较提示抽取与激活探测对推荐系统数据记忆的检出

    arXiv
    2601.02002
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    LLaMA-1B, LLaMA-3B
    Abstract作者称自动优化提示最有希望抽出影片，但数值字段和高分都不能确认泄漏。

    作者比较越狱、激活探测和自动提示，看公开 LLaMA 能否抽出或检出 MovieLens-1M 中的记忆。

    Paper analysisRead analysis
You have reached the end