Private distribution testing with heterogeneous constraints: Your epsilon might not be mine


Loading...

Date

2024-01-24

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric

Data

Abstract

Private closeness testing asks to decide whether the underlying probability distributions of two sensitive datasets are identical or differ significantly in statistical distance, while guaranteeing (differential) privacy of the data. As in most (if not all) distribution testing questions studied under privacy constraints, however, previous work assumes that the two datasets are equally sensitive, i.e., must be provided the same privacy guarantees. This is often an unrealistic assumption, as different sources of data come with different privacy requirements; as a result, known closeness testing algorithms might be unnecessarily conservative, "paying" too high a privacy budget for half of the data. In this work, we initiate the study of the closeness testing problem under heterogeneous privacy constraints, where the two datasets come with distinct privacy requirements. We formalize the question and provide algorithms under the three most widely used differential privacy settings, with a particular focus on the local and shuffle models of privacy; and show that one can indeed achieve better sample efficiency when taking into account the two different "epsilon" requirements.

Publication status

published

Book title

15th Innovations in Theoretical Computer Science Conference (ITCS 2024)

Volume

287

Pages / Article No.

Publisher

Schloss Dagstuhl – Leibniz-Zentrum für Informatik

Event

15th Innovations in Theoretical Computer Science Conference (ITCS 2024)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Differential privacy; Distribution testing; Local privacy; Shuffle privacy

Organisational unit

Notes

Funding

Related publications and datasets