BriefGPT.xyz
May, 2024
面向扩散模型的黑盒成员推断攻击
Towards Black-Box Membership Inference Attack for Diffusion Models
HTML
PDF
Jingwei Li, Jing Dong, Tianxing He, Jingzhao Zhang
TL;DR
通过黑盒成员推断攻击方法，在不需要访问模型的内部 U-net 的情况下，构建了一个 DALL-E 生成的数据集进行全面评估，实验结果优于以前的研究。
Abstract
Identifying whether an artwork was used to train a diffusion model is an important research topic, given the rising popularity of
ai-generated art
and the associated
copyright concerns
. The work approaches this p
→