PriSampler: Mitigating Property Inference of Diffusion Models

arXiv:2306.05208v2 Announce Type: replace
Abstract: Diffusion models have been remarkably successful in data synthesis. However, when these models are applied to sensitive datasets, such as banking and human face data, they might bring up severe privacy concerns. This work systematically presents the first privacy study about property inference attacks against diffusion models, where adversaries aim to extract sensitive global properties of its training set from a diffusion model. Specifically, we focus on the most practical attack scenario: adversaries are restricted …

arxiv attacks banking cs.cr cs.cv cs.lg data datasets diffusion models human privacy privacy concerns property sensitive study work