UM  > Faculty of Science and Technology
Affiliated with RCfalse
Status已發表Published
Privacy-Preserving distributed deep learning based on secret sharing
Jia Duan1; Jiantao Zhou1; Yuanman Li2
2020-03-26
Source PublicationInformation Sciences
ISSN0020-0255
Volume527Pages:108-127
Abstract

Distributed deep learning (DDL) naturally provides a privacy-preserving solution to enable multiple parties to jointly learn a deep model without explicitly sharing the local datasets. However, the existing privacy-preserving DDL schemes still suffer from severe information leakage and/or lead to significant increase of the communication cost. In this work, we design a privacy-preserving DDL framework such that all the participants can keep their local datasets private with low communication and computational cost, while still maintaining the accuracy and efficiency of the learned model. By adopting an effective secret sharing strategy, we allow each participant to split the intervening parameters in the training process into shares and upload an aggregation result to the cloud server. We can theoretically show that the local dataset of a particular participant can be well protected against the honest-but-curious cloud server as well as the other participants, even under the challenging case that the cloud server colludes with some participants. Extensive experimental results are provided to validate the superiority of the proposed secret sharing based distributed deep learning (SSDDL) framework.

KeywordDeep Neural Network Distributed Deep Learning Privacy Preserving Secret Sharing Secure Multi-party Computation
DOI10.1016/j.ins.2020.03.074
URLView the original
Indexed BySCIE
Language英語English
WOS Research AreaComputer Science
WOS SubjectComputer Science, Information Systems
WOS IDWOS:000532695700006
Scopus ID2-s2.0-85083001468
Fulltext Access
Citation statistics
Cited Times [WOS]:10   [WOS Record]     [Related Records in WOS]
Document TypeJournal article
CollectionFaculty of Science and Technology
Corresponding AuthorJiantao Zhou
Affiliation1.State Key Laboratory of Internet of Things for Smart City,Department of Computer and Information Science,Faculty of Science and Technology,University of Macau,China
2.College of Electronics and Information Engineering,Shenzhen University,China
First Author AffilicationFaculty of Science and Technology
Corresponding Author AffilicationFaculty of Science and Technology
Recommended Citation
GB/T 7714
Jia Duan,Jiantao Zhou,Yuanman Li. Privacy-Preserving distributed deep learning based on secret sharing[J]. Information Sciences,2020,527:108-127.
APA Jia Duan,Jiantao Zhou,&Yuanman Li.(2020).Privacy-Preserving distributed deep learning based on secret sharing.Information Sciences,527,108-127.
MLA Jia Duan,et al."Privacy-Preserving distributed deep learning based on secret sharing".Information Sciences 527(2020):108-127.
Files in This Item: Download All
File Name/Size Publications Version Access License
Privacy-Preserving d(2207KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Jia Duan]'s Articles
[Jiantao Zhou]'s Articles
[Yuanman Li]'s Articles
Baidu academic
Similar articles in Baidu academic
[Jia Duan]'s Articles
[Jiantao Zhou]'s Articles
[Yuanman Li]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Jia Duan]'s Articles
[Jiantao Zhou]'s Articles
[Yuanman Li]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Privacy-Preserving distributed deep learning based on secret sharing.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.