Papers › Differentially Private Generation of Small Images

Differentially Private Generation of Small Images

2 May 2020arXiv:2005.00783archive 2025-07-28

Justus T. C. Schwabedal, Pascal Michel, Mario S. Riontino

We explore the training of generative adversarial networks with differential privacy to anonymize image data sets. On MNIST, we numerically measure the privacy-utility trade-off using parameters from ϵ-δ differential privacy and the inception score. Our experiments uncover a saturated training regime where an increasing privacy budget adds little to the quality of generated images. We also explain analytically why differentially private Adam optimization is independent of the gradient clipping parameter. Furthermore, we highlight common errors in previous works on differentially private deep learning, which we uncovered in recent literature. Throughout the treatment of the subject, we hope to prevent erroneous estimates of anonymity in the future.

PaperPDFCode

Code

jusjusjus/noise-in-dpsgd-2020 officialmentioned in paperpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamGradient Clipping

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections