Skip to content

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

Oct 12 · Monday

Defenses and guardrails · Papers

Found 1 paper
Filter3

System type

Models and APIs1coding agent0

System component

Guardrails and judges12Monitors9Reasoning chains5Fine-tuning and open weights3Vision9Image generation1Multimodal12
Select any value within a category; different categories must all match. Counts include the other filters you have selected.
System type：Models and APIsSystem type：coding agentSystem component：Image generationTopic: Defenses and guardrailsClear all
  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