On one hand, the local data of users may contain sensitive information, and privacy-preserving mechanisms are needed.

Recent works have shown that a wide range of differential privacy mechanisms can be "simulated"

The advancement of machine learning (ML) techniques relies on large amounts of training data. However, data collection also poses a significant risk of exposing private information.

However, differential privacy's worst-case nature entails scaling such noise to the range of the queries even for

However, differential privacy's worst-case nature entails scaling such noise to the range of the queries even for

A fundamental result in differential privacy states that the privacy guarantees of a mechanism are preserved by any post-processing of its output. In this paper we investigate under what conditions stochastic post-processing can amplify the privacy of a mechanism. By interpreting post-processing as the application of a Markov operator, we first give a series of amplification results in terms of uniform mixing properties of the Markov process defined by said operator. Next we provide amplification bounds in terms of coupling arguments which can be applied in cases where uniform mixing is not available. Finally, we introduce a new family of mechanisms based on diffusion processes which are closed under post-processing, and analyze their privacy via a novel heat flow argument. On the applied side, we generalize the analysis of "privacy amplification by iteration" in Noisy SGD and show it admits an exponential improvement in the strongly convex case, and study a mechanism based on the Ornstein-Uhlenbeck diffusion process which contains the Gaussian mechanism with optimal post-processing on bounded inputs as a special case.