Exact Privacy Analysis of the Gaussian Sparse Histogram Mechanism

Sparse histogram methods can be useful for returning differentially private counts of items in large or infinite histograms, large group-by queries, and more generally, releasing a set of statistics with sufficient item counts. We consider the Gaussian version of the sparse histogram mechanism and s...

Full description

Saved in:
Bibliographic Details
Published inThe journal of privacy and confidentiality Vol. 14; no. 1
Main Authors Wilkins, Arjun, Kifer, Daniel, Zhang, Danfeng, Karrer, Brian
Format Journal Article
LanguageEnglish
Published Labor Dynamics Institute 11.02.2024
Subjects
differential privacy
gaussian mechanism
sparse histogram mechanism
Online AccessGet full text

Cover

More Information
Summary:Sparse histogram methods can be useful for returning differentially private counts of items in large or infinite histograms, large group-by queries, and more generally, releasing a set of statistics with sufficient item counts. We consider the Gaussian version of the sparse histogram mechanism and study the exact epsilon, delta differential privacy guarantees satisfied by this mechanism. We compare these exact epsilon, delta parameters to the simpler overestimates used in prior work to quantify the impact of their looser privacy bounds.
ISSN:2575-8527
2575-8527
DOI:10.29012/jpc.823