Can collaborative learning be private, robust and scalable?

no code implementations • 5 May 2022 • Dmitrii Usynin, Helena Klause, Johannes C. Paetzold, Daniel Rueckert, Georgios Kaissis

In federated learning for medical image analysis, the safety of the learning protocol is paramount.

Adversarial Robustness Federated Learning +1

Differentially private training of residual networks with scale normalisation

no code implementations • 1 Mar 2022 • Helena Klause, Alexander Ziller, Daniel Rueckert, Kerstin Hammernik, Georgios Kaissis

The training of neural networks with Differentially Private Stochastic Gradient Descent offers formal Differential Privacy guarantees but introduces accuracy trade-offs.