The Discrete Gaussian for Differential Privacy

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Canonne, Clément L., Kamath, Gautam, Steinke, Thomas
Format: Preprint
Publié: 2020
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916483635871744
author Canonne, Clément L.
Kamath, Gautam
Steinke, Thomas
author_facet Canonne, Clément L.
Kamath, Gautam
Steinke, Thomas
contents A key tool for building differentially private systems is adding Gaussian noise to the output of a function evaluated on a sensitive dataset. Unfortunately, using a continuous distribution presents several practical challenges. First and foremost, finite computers cannot exactly represent samples from continuous distributions, and previous work has demonstrated that seemingly innocuous numerical errors can entirely destroy privacy. Moreover, when the underlying data is itself discrete (e.g., population counts), adding continuous noise makes the result less interpretable. With these shortcomings in mind, we introduce and analyze the discrete Gaussian in the context of differential privacy. Specifically, we theoretically and experimentally show that adding discrete Gaussian noise provides essentially the same privacy and accuracy guarantees as the addition of continuous Gaussian noise. We also present an simple and efficient algorithm for exact sampling from this distribution. This demonstrates its applicability for privately answering counting queries, or more generally, low-sensitivity integer-valued queries.
format Preprint
id arxiv_https___arxiv_org_abs_2004_00010
institution arXiv
publishDate 2020
record_format arxiv
spellingShingle The Discrete Gaussian for Differential Privacy
Canonne, Clément L.
Kamath, Gautam
Steinke, Thomas
Data Structures and Algorithms
Cryptography and Security
Machine Learning
A key tool for building differentially private systems is adding Gaussian noise to the output of a function evaluated on a sensitive dataset. Unfortunately, using a continuous distribution presents several practical challenges. First and foremost, finite computers cannot exactly represent samples from continuous distributions, and previous work has demonstrated that seemingly innocuous numerical errors can entirely destroy privacy. Moreover, when the underlying data is itself discrete (e.g., population counts), adding continuous noise makes the result less interpretable. With these shortcomings in mind, we introduce and analyze the discrete Gaussian in the context of differential privacy. Specifically, we theoretically and experimentally show that adding discrete Gaussian noise provides essentially the same privacy and accuracy guarantees as the addition of continuous Gaussian noise. We also present an simple and efficient algorithm for exact sampling from this distribution. This demonstrates its applicability for privately answering counting queries, or more generally, low-sensitivity integer-valued queries.
title The Discrete Gaussian for Differential Privacy
topic Data Structures and Algorithms
Cryptography and Security
Machine Learning
url https://arxiv.org/abs/2004.00010