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

Jailbreaks1Poisoning and backdoors11Extraction and theft3Detection evasion4

Layer

Prompt layer54Model layer13Application layer6Training and data layer1

System component

Monitors0Embeddings0Multimodal1
Select any value within a category; different categories must all match. Counts include the other filters you have selected.Another 215papers have no tags yet and are not included in filtered results.
Attack type：JailbreaksLayer：Training and data layerSystem component：MonitorsSystem component：EmbeddingsSystem component：MultimodalClear all

Another 215papers do not have category tags yet and are not included in filtered results.

  1. DefensesarXiv 2610.05401

    AVCE：面向扩散模型可验证概念擦除的审计感知遗忘框架

    提出审计感知遗忘框架 AVCE，从文本与视觉通路擦除扩散模型概念

    arXiv
    2610.05401
    Published
    Layer
    Training and data layer
    Setting
    Models and APIs
    Attacker
    White-box, Black-box
    Evaluated models
    Stable Diffusion XL (SDXL), Stable Diffusion v1.5 (SD v1.5), Flux 1.0
    AbstractAVCE 在审计锚点上改两条注意力通路。

    AVCE 是面向扩散模型的概念擦除方法，要让擦除经得起绕过文本条件的潜空间审计，而不只是挡住对抗提示词。

    Paper analysisRead analysis
You have reached the end