Differentially Private Normalizing Flows for Privacy-Preserving Density Estimation

Normalizing flow models have risen as a popular solution to the problem of density estimation, enabling high-quality synthetic data generation as well as exact probability density evaluation. However, in contexts where individuals are directly associated with the training data, releasing such a mode...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Waites, Chris, Cummings, Rachel
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 25.03.2021
Subjects
Algorithms
Anomalies
Density
Privacy
Online AccessGet full text

Cover

More Information
Summary:Normalizing flow models have risen as a popular solution to the problem of density estimation, enabling high-quality synthetic data generation as well as exact probability density evaluation. However, in contexts where individuals are directly associated with the training data, releasing such a model raises privacy concerns. In this work, we propose the use of normalizing flow models that provide explicit differential privacy guarantees as a novel approach to the problem of privacy-preserving density estimation. We evaluate the efficacy of our approach empirically using benchmark datasets, and we demonstrate that our method substantially outperforms previous state-of-the-art approaches. We additionally show how our algorithm can be applied to the task of differentially private anomaly detection.
ISSN:2331-8422