SecDD: Efficient and Secure Method for Remotely Training Neural Networks

09/19/2020

∙

by   Ilia Sucholutsky, et al.

∙

1

∙

share

We leverage what are typically considered the worst qualities of deep learning algorithms - high computational cost, requirement for large data, no explainability, high dependence on hyper-parameter choice, overfitting, and vulnerability to adversarial perturbations - in order to create a method for the secure and efficient training of remotely deployed neural networks over unsecured channels.