Privacy-preserving distributed deep learning with privacy transformations

Sen Ching S. Cheung, Muhammad Usman Rafique, Wai Tian Tan

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

Distributed Deep Learning (DDL) allows disparate sites or entities to use their local data to collaboratively learn a model at a central server. To protect data privacy, existing approaches like fully homomorphic encryption and differential privacy are either computationally prohibitive or insecure. In this paper, we proposed applying a privacy-preserving transformation (PPT) before sending the transformed data to the server. The design goals of PPT include computation efficiency, privacy preservation, and good learnability at the server with maximal reuse of DL software infrastructure. After analyzing the security model and possible attacks, we evaluated simple PPTs including scrambling, random linear transforms, and Advanced Encryption Standard (AES). While AES is more secure than the others, it significantly degrades the learning performance. To address this challenge, we proposed a novel random deep neural network as PPT. Our experiments showed that the random weights and connections provide adequate security and good learning performances at the server.

Original languageEnglish
Title of host publication10th IEEE International Workshop on Information Forensics and Security, WIFS 2018
ISBN (Electronic)9781538665367
DOIs
StatePublished - Jul 2 2018
Event10th IEEE International Workshop on Information Forensics and Security, WIFS 2018 - Hong Kong, Hong Kong
Duration: Dec 10 2018Dec 13 2018

Publication series

Name10th IEEE International Workshop on Information Forensics and Security, WIFS 2018

Conference

Conference10th IEEE International Workshop on Information Forensics and Security, WIFS 2018
Country/TerritoryHong Kong
CityHong Kong
Period12/10/1812/13/18

Bibliographical note

Publisher Copyright:
© 2018 IEEE.

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Law
  • Information Systems and Management
  • Safety, Risk, Reliability and Quality

Fingerprint

Dive into the research topics of 'Privacy-preserving distributed deep learning with privacy transformations'. Together they form a unique fingerprint.

Cite this