SecDD: Efficient and Secure Method for Remotely Training Neural Networks

2020/09/19 by Sucholutsky, Ilia, Schonlau, Matthias · 1 citation
#FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning (stat.ML)

paper · doi:10.48550/arxiv.2009.09155

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.

Cited by

• MGD³: Mode-Guided Dataset Distillation using Diffusion Models

Related

• S++: A Fast and Deployable Secure-Computation Framework for Privacy-Preserving Neural Network Training
• Neural Network Training on Encrypted Data with TFHE
• Fast Training of Provably Robust Neural Networks by SingleProp
• SecONNds: Secure Outsourced Neural Network Inference on ImageNet
• No Peek: A Survey of private distributed deep learning