SecDD: Efficient and Secure Method for Remotely Training Neural Networks
Machine Learning
2020-09-22 v1 Machine Learning
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.
Cite
@article{arxiv.2009.09155,
title = {SecDD: Efficient and Secure Method for Remotely Training Neural Networks},
author = {Ilia Sucholutsky and Matthias Schonlau},
journal= {arXiv preprint arXiv:2009.09155},
year = {2020}
}
Comments
2 pages, 1 figure