Work

Rényi Differential Privacy of the Sampled Gaussian Mechanism

Year: 2019
Type: preprint
Abstract: The Sampled Gaussian Mechanism (SGM)---a composition of subsampling and the additive Gaussian noise---has been successfully used in a number of machine learning applications. The mechanism's unexpected power is derived from privacy amplification by sampling where the privacy cost of a single evaluation diminishes quadratically, rather than linearly, with the sampling rate. Characterizing the precise privacy properties of SGM motivated development of several relaxations of the notion of differential privacy. This work unifies and fills in gaps in published results on SGM. We describe a numerically stable procedure for precise computation of SGM's Rényi Differential Privacy and prove a nearly tight (within a small constant factor) closed-form bound.
Language: English
Open Access status: green
OpenAlex ID: W2970055833
Cites: 10
Cited by: 421
Related to: 9