Cryptology ePrint Archive: Report 2017/762

Private Collaborative Neural Network Learning

Melissa Chase and Ran Gilad-Bachrach and Kim Laine and Kristin Lauter and Peter Rindal

Abstract: Machine learning algorithms, such as neural networks, create better predictive models when having access to larger datasets. In many domains, such as medicine and finance, each institute has only access to limited amounts of data, and creating larger datasets typically requires collaboration. However, there are privacy related constraints on these collaborations for legal, ethical, and competitive reasons. In this work, we present a feasible protocol for learning neural networks in a collaborative way while preserving the privacy of each record. This is achieved by combining Differential Privacy and Secure Multi-Party Computation with Machine Learning.

Category / Keywords: applications / deep learning, neural networks, differential privacy, secure multi-party computation

Date: received 7 Aug 2017

Contact author: kim laine at microsoft com

Available format(s): PDF | BibTeX Citation

Version: 20170808:183434 (All versions of this report)

Short URL:

[ Cryptology ePrint archive ]