While diffusion models have recently demonstrated remarkable progress in
generating realistic images, privacy risks also arise: published models or APIs
could generate training images and thus leak privacy-sensitive training
information. In this paper, we reveal a new risk, Shake-to-Leak (S2L), that
fine-tuning the pre-trained models with manipulated data can amplify the
existing privacy risks. We demonstrate that S2L could occur in various standard
fine-tuning strategies for diffusion models, including concept-injection
methods (DreamBooth and Textual Inversion) and parameter-efficient methods
(LoRA and Hypernetwork), as well as their combinations. In the worst case, S2L
can amplify the state-of-the-art membership inference attack (MIA) on diffusion
models by $5.4\%$ (absolute difference) AUC and can increase extracted private
samples from almost $0$ samples to $16.3$ samples on average per target domain.
This discovery underscores that the privacy risk with diffusion models is even
more severe than previously recognized. Codes are available at
this https URL

扩散模型存在隐私风险，其中 Shake-to-Leak (S2L) 是一种新的风险，通过操纵数据以微调预训练模型，可以增强现有的隐私风险，尤其在扩散模型下还比过去认识的更严重。