Private, Yet Practical, Multiparty Deep Learning

Xinyang Zhang, Shouling Ji, Hui Wang, Ting Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

11 Scopus citations

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 threshold secret sharing. Compared with prior work, ∝MDL departs in significant ways: a) besides providing explicit privacy guarantee, it retains desirable model utility, which is paramount for accuracy-critical domains; b) it provides an intuitive handle for the operator to gracefully balance model utility and training efficiency; c) moreover, it supports delicate control over communication and computational costs by offering two variants, operating under loose and tight coordination respectively, thus optimizable for given system settings (e.g., limited versus sufficient network bandwidth). Through extensive empirical evaluation using benchmark datasets and deep learning architectures, we demonstrate the efficacy of ∝MDL.

Original languageEnglish (US)
Title of host publicationProceedings - IEEE 37th International Conference on Distributed Computing Systems, ICDCS 2017
EditorsKisung Lee, Ling Liu
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1442-1452
Number of pages11
ISBN (Electronic)9781538617915
DOIs
StatePublished - Jul 13 2017
Event37th IEEE International Conference on Distributed Computing Systems, ICDCS 2017 - Atlanta, United States
Duration: Jun 5 2017Jun 8 2017

Publication series

NameProceedings - International Conference on Distributed Computing Systems

Other

Other37th IEEE International Conference on Distributed Computing Systems, ICDCS 2017
CountryUnited States
CityAtlanta
Period6/5/176/8/17

All Science Journal Classification (ASJC) codes

  • Software
  • Hardware and Architecture
  • Computer Networks and Communications

Fingerprint Dive into the research topics of 'Private, Yet Practical, Multiparty Deep Learning'. Together they form a unique fingerprint.

  • Cite this

    Zhang, X., Ji, S., Wang, H., & Wang, T. (2017). Private, Yet Practical, Multiparty Deep Learning. In K. Lee, & L. Liu (Eds.), Proceedings - IEEE 37th International Conference on Distributed Computing Systems, ICDCS 2017 (pp. 1442-1452). [7980083] (Proceedings - International Conference on Distributed Computing Systems). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICDCS.2017.215