most citedSmoothNets: Optimizing CNN architecture design for differentially private deep learning

3 citations · 5 across the 2 of their papers we have counts for

collaborators

2 papers

cs.CV2022★ 3 cited

SmoothNets: Optimizing CNN architecture design for differentially private deep learning

Nicolas W. Remerscheid, Alexander Ziller, Daniel Rueckert +1

The arguably most widely employed algorithm to train deep neural networks with Differential Privacy is DPSGD, which requires clipping and noising of per-sample gradients. This intr…

eess.IV2021★ 2 cited

Differentially private federated deep learning for multi-site medical image segmentation

Alexander Ziller, Dmitrii Usynin, Nicolas Remerscheid +5

Collaborative machine learning techniques such as federated learning (FL) enable the training of models on effectively larger datasets without data transfer. Recent initiatives hav…