The Elusive Pursuit of Reproducing PATE-GAN: Benchmarking, Auditing, Debugging

TL;DR

This paper critically evaluates PATE-GAN implementations, revealing significant deviations from original utility claims and privacy leaks, through benchmarking, auditing, and debugging of six open-source versions.

Contribution

It provides the first comprehensive benchmarking, privacy auditing, and bug analysis of multiple PATE-GAN implementations, highlighting discrepancies and privacy risks.

Findings

None of the implementations match original utility performance.

All implementations leak more privacy than intended.

Multiple bugs and privacy violations were identified.

Abstract

Synthetic data created by differentially private (DP) generative models is increasingly used in real-world settings. In this context, PATE-GAN has emerged as one of the most popular algorithms, combining Generative Adversarial Networks (GANs) with the private training approach of PATE (Private Aggregation of Teacher Ensembles). In this paper, we set out to reproduce the utility evaluation from the original PATE-GAN paper, compare available implementations, and conduct a privacy audit. More precisely, we analyze and benchmark six open-source PATE-GAN implementations, including three by (a subset of) the original authors. First, we shed light on architecture deviations and empirically demonstrate that none reproduce the utility performance reported in the original paper. We then present an in-depth privacy evaluation, which includes DP auditing, and show that all implementations leak more privacy than intended. Furthermore, we uncover 19 privacy violations and 5 other bugs in these six open-source implementations. Lastly, our codebase is available from: https://github.com/spalabucr/pategan-audit.