Skip to content

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

Oct 12 · Monday

All papers

Found 1 paper
Filter4

Defense type

Model hardening4Detection and filtering1

Attack surface / entry point

User input5Images, audio and video13Training data1

System component

Monitors0Multimodal1
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.
Defense type：Detection and filteringAttack surface / entry point：Training dataSystem component：MonitorsSystem component：MultimodalClear all

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

  1. DefensesarXiv 2609.06346

    面向后门攻击下持续学习的鲁棒动态扩展：净化与选择性恢复

    提出持续学习下的净化与选择性恢复框架，抵御逐任务训练投毒后门

    arXiv
    2609.06346
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Evaluated models
    ViT-B/16
    Abstract作者报告任务内净化与恢复可配合动态专家防御后门，但保证依赖分离条件。

    这是一项面向持续图像分类的后门防御研究：模型只使用当前任务数据，同时需要保留过去知识并避免学习恶意监督。

    Paper analysisRead analysis
You have reached the end