Skip to content

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

Oct 13 · Tuesday

All papers

Found 1 paper
Filter5

Attack type

Poisoning and backdoors6Extraction and theft1

Attack surface / entry point

User input20Tool and skill descriptions0Memory writes0Training data1Weights and gradients5

Layer

Model layer1Training and data layer6
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 216papers have no tags yet and are not included in filtered results.
Attack type：Extraction and theftAttack surface / entry point：Tool and skill descriptionsAttack surface / entry point：Memory writesAttack surface / entry point：Training dataLayer：Model layerClear all

Another 216papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2610.04426

    UnAct：无需梯度的定向激活干预实现类别遗忘

    提出 UnAct，仅以前向激活干预从分类器中遗忘指定类别

    arXiv
    2610.04426
    Published
    Layer
    Model layer
    Setting
    Models and APIs
    Evaluated models
    ResNet-18, ViT-B/16
    AbstractUnAct 用前向激活做类别遗忘。

    UnAct 是一种事后类别遗忘：删除请求可以只有少量该类图像，且没有标签和保留数据。它不用梯度，只对遗忘图像做前向。编辑对象是分类器所读的后期单元。

    Paper analysisRead analysis
You have reached the end