Membership Inference of Diffusion Models. (arXiv:2301.09956v1 [cs.CR])

Recent years have witnessed the tremendous success of diffusion models in
data synthesis. However, when diffusion models are applied to sensitive data,
they also give rise to severe privacy concerns. In this paper, we
systematically present the first study about membership inference attacks
against diffusion models, which aims to infer whether a sample was used to
train the model. Two attack methods are proposed, namely loss-based and
likelihood-based attacks. Our attack methods are evaluated on several
state-of-the-art diffusion models, over …

attack attacks data diffusion models loss privacy sensitive data study train