Papers › On the effect of normalization layers on Differentially Private training of deep...

On the effect of normalization layers on Differentially Private training of deep Neural networks

19 Jun 2020arXiv:2006.10919archive 2025-07-28

Ali Davody, David Ifeoluwa Adelani, Thomas Kleinbauer, Dietrich Klakow

Differentially private stochastic gradient descent (DPSGD) is a variation of stochastic gradient descent based on the Differential Privacy (DP) paradigm, which can mitigate privacy threats that arise from the presence of sensitive information in training data. However, one major drawback of training deep neural networks with DPSGD is a reduction in the models accuracy. In this paper, we study the effect of normalization layers on the performance of DPSGD. We demonstrate that normalization layers significantly impact the utility of deep neural networks with noisy parameters and should be considered essential ingredients of training with DPSGD. In particular, we propose a novel method for integrating batch normalization with DPSGD without incurring an additional privacy loss. With our approach, we are able to train deeper networks and achieve a better utility-privacy trade-off.

PaperPDFCode

Code

uds-lsv/SIDP officialmentioned in papermentioned on GitHubpytorch 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

Layer Normalization

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