PAC Privacy Preserving Diffusion Models
CoRR(2023)
摘要
Data privacy protection is garnering increased attention among researchers.
Diffusion models (DMs), particularly with strict differential privacy, can
potentially produce images with both high privacy and visual quality. However,
challenges arise in ensuring robust protection in privatizing specific data
attributes, areas where current models often fall short. To address these
challenges, we introduce the PAC Privacy Preserving Diffusion Model, a model
leverages diffusion principles and ensure Probably Approximately Correct (PAC)
privacy. We enhance privacy protection by integrating a private classifier
guidance into the Langevin Sampling Process. Additionally, recognizing the gap
in measuring the privacy of models, we have developed a novel metric to gauge
privacy levels. Our model, assessed with this new metric and supported by
Gaussian matrix computations for the PAC bound, has shown superior performance
in privacy protection over existing leading private generative models according
to benchmark tests.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要