SecDD: Efficient and Secure Method for Remotely Training Neural Networks

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.

2 pages, 1 figure

References in corpus (6)

• Dataset Condensation with Gradient Matching
• Soft-Label Dataset Distillation and Text Dataset Distillation
• Hyperspherical Prototype Networks
• Optimizing Millions of Hyperparameters by Implicit Differentiation
• Flexible Dataset Distillation: Learn Labels Instead of Images
• Using Small Proxy Datasets to Accelerate Hyperparameter Search