Skip to content

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

Oct 12 · Monday

All papers

Found 3 papers
Filter3

Defense type

Model hardening3Detection and filtering3

System type

Models and APIs3

Attacker access

White-box3

Attack surface / entry point

User input7Images, audio and video3Training data5Weights and gradients6
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 265papers have no tags yet and are not included in filtered results.
Defense type：Model hardeningAttacker access：White-boxAttack surface / entry point：Images, audio and videoClear all

Another 265papers do not have category tags yet and are not included in filtered results.

  3. DefensesarXiv 2609.23596

    StyleAT：用对抗训练防御人脸识别的语义攻击

    提出 BoundStyle 与 StyleAT，对抗训练防御人脸识别语义攻击

    arXiv
    2609.23596
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Attacker
    White-box, Black-box
    Evaluated models
    MobileFaceNet (MobileFace), ResNet (ResNet-152, IR-SE), RepVGG and others7
    AbstractBoundStyle 用 StyleGAN3 有界潜编辑快速攻击 FR。

    StyleAT 用可调的 StyleGAN3 潜空间攻击 BoundStyle 对人脸识别做对抗训练，以抵抗一般语义编辑，并在评测中面对训练时未见的 DiffPrivate。

    Paper analysisRead analysis
You have reached the end