Skip to content

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

Oct 12 · Monday

All papers

Found 1 paper
Filter3

Attack type

Jailbreaks7Detection evasion1

Defense type

Model hardening1Detection and filtering6

Attacker access

Black-box1
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.
Attack type：Detection evasionDefense type：Model hardeningAttacker access：Black-boxClear all

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

  1. 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