Private distribution testing with heterogeneous constraints: Your epsilon might not be mine
OPEN ACCESS
Loading...
Author / Producer
Date
2024-01-24
Publication Type
Conference Paper
ETH Bibliography
yes
Citations
Altmetric
OPEN ACCESS
Data
Rights / License
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.
Permanent link
Publication status
published
External links
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