Differentially Private Normalizing Flows for Privacy-Preserving Density Estimation
This work addresses privacy concerns for individuals associated with training data in density estimation tasks, offering a novel approach with explicit differential privacy guarantees.
The authors tackled the problem of privacy-preserving density estimation by proposing differentially private normalizing flow models, demonstrating that their method substantially outperforms previous state-of-the-art approaches on benchmark datasets.
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.