Enregistré dans:
Détails bibliographiques
Auteurs principaux: Chen, E, Cao, Yang, Ge, Yifei
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2401.04306
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916085348958208
author Chen, E
Cao, Yang
Ge, Yifei
author_facet Chen, E
Cao, Yang
Ge, Yifei
contents The shuffle model of Differential Privacy (DP) has gained significant attention in privacy-preserving data analysis due to its remarkable tradeoff between privacy and utility. It is characterized by adding a shuffling procedure after each user's locally differentially private perturbation, which leads to a privacy amplification effect, meaning that the privacy guarantee of a small level of noise, say $ε_0$, can be enhanced to $O(ε_0/\sqrt{n})$ (the smaller, the more private) after shuffling all $n$ users' perturbed data. Most studies in the shuffle DP focus on proving a tighter privacy guarantee of privacy amplification. However, the current results assume that the local privacy budget $ε_0$ is within a limited range. In addition, there remains a gap between the tightest lower bound and the known upper bound of the privacy amplification. In this work, we push forward the state-of-the-art by making the following contributions. Firstly, we present the first asymptotically optimal analysis of Renyi Differential Privacy (RDP) in the shuffle model without constraints on $ε_0$. Secondly, we introduce hypothesis testing for privacy amplification through shuffling, offering a distinct analysis technique and a tighter upper bound. Furthermore, we propose a DP-SGD algorithm based on RDP. Experiments demonstrate that our approach outperforms existing methods significantly at the same privacy level.
format Preprint
id arxiv_https___arxiv_org_abs_2401_04306
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Renyi Differential Privacy in the Shuffle Model: Enhanced Amplification Bounds
Chen, E
Cao, Yang
Ge, Yifei
Combinatorics
The shuffle model of Differential Privacy (DP) has gained significant attention in privacy-preserving data analysis due to its remarkable tradeoff between privacy and utility. It is characterized by adding a shuffling procedure after each user's locally differentially private perturbation, which leads to a privacy amplification effect, meaning that the privacy guarantee of a small level of noise, say $ε_0$, can be enhanced to $O(ε_0/\sqrt{n})$ (the smaller, the more private) after shuffling all $n$ users' perturbed data. Most studies in the shuffle DP focus on proving a tighter privacy guarantee of privacy amplification. However, the current results assume that the local privacy budget $ε_0$ is within a limited range. In addition, there remains a gap between the tightest lower bound and the known upper bound of the privacy amplification. In this work, we push forward the state-of-the-art by making the following contributions. Firstly, we present the first asymptotically optimal analysis of Renyi Differential Privacy (RDP) in the shuffle model without constraints on $ε_0$. Secondly, we introduce hypothesis testing for privacy amplification through shuffling, offering a distinct analysis technique and a tighter upper bound. Furthermore, we propose a DP-SGD algorithm based on RDP. Experiments demonstrate that our approach outperforms existing methods significantly at the same privacy level.
title Renyi Differential Privacy in the Shuffle Model: Enhanced Amplification Bounds
topic Combinatorics
url https://arxiv.org/abs/2401.04306