Private, Yet Practical, Multiparty Deep Learning

Abstract

In this paper, we consider the problem of multiparty deep learning (MDL), wherein autonomous data owners jointly train accurate deep neural network models without sharing their private data. We design, implement, and evaluate ∝MDL, a new MDL paradigm built upon three primitives: asynchronous optimization, lightweight homomorphic encryption, and… (More)
DOI: 10.1109/ICDCS.2017.215

Topics

10 Figures and Tables

Cite this paper

@article{Zhang2017PrivateYP, title={Private, Yet Practical, Multiparty Deep Learning}, author={Xinyang Zhang and Shouling Ji and Hui Wang and Ting Wang}, journal={2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS)}, year={2017}, pages={1442-1452} }