SecDD: Efficient and Secure Method for Remotely Training Neural Networks

Code

• github.com/ilia10000/dataset-distillation
  Officialpytorch★ 74

Abstract

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.

Reproductions