Cryptology ePrint Archive: Report 2019/140

CodedPrivateML: A Fast and Privacy-Preserving Framework for Distributed Machine Learning

Jinhyun So and Basak Guler and A. Salman Avestimehr and Payman Mohassel

Abstract: How to train a machine learning model while keeping the data private and secure? We present CodedPrivateML, a fast and scalable approach to this critical problem. CodedPrivateML keeps both the data and the model information-theoretically private, while allowing efficient parallelization of training across distributed workers. We characterize CodedPrivateML's privacy threshold and prove its convergence for logistic (and linear) regression. Furthermore, via experiments over Amazon EC2, we demonstrate that CodedPrivateML can provide an order of magnitude speedup (up to $\sim 34\times$) over the state-of-the-art cryptographic approaches.

Category / Keywords: applications / privacy-preserving machine learning, information-theoretic privacy

Original Publication (in the same form): arXiv:1902.00641

Date: received 6 Feb 2019

Contact author: jinhyuns at usc edu, bguler@usc edu

Available format(s): PDF | BibTeX Citation

Version: 20190214:185232 (All versions of this report)

Short URL: ia.cr/2019/140


[ Cryptology ePrint archive ]