Blind Faith: Privacy-Preserving Machine Learning using Function Approximation

Tanveer Khan, Alexandros Bakas, Antonis Michalas

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

10 Citations (Scopus)
19 Downloads (Pure)

Abstract

Over the past few years, a tremendous growth of machine learning was brought about by a significant increase in adoption of cloud-based services. As a result, various solutions have been proposed in which the machine learning models run on a remote cloud provider. However, when such a model is deployed on an untrusted cloud, it is of vital importance that the users' privacy is preserved. To this end, we propose Blind Faith - a machine learning model in which the training phase occurs in plaintext data, but the classification of the users' inputs is performed on homomorphically encrypted ciphertexts. To make our construction compatible with homomorphic encryption, we approximate the activation functions using Chebyshev polynomials. This allowed us to build a privacy-preserving machine learning model that can classify encrypted images. Blind Faith preserves users' privacy since it can perform high accuracy predictions by performing computations directly on encrypted data.
Original languageEnglish
Title of host publication2021 IEEE Symposium on Computers and Communications (ISCC)
PublisherIEEE
Pages1-7
Number of pages7
ISBN (Electronic)978-1-6654-2744-9
DOIs
Publication statusPublished - 2021
Publication typeA4 Article in conference proceedings
Event IEEE Symposium on Computers and Communications - , Greece
Duration: 5 Sept 20218 Sept 2021

Publication series

NameProceedings : IEEE Symposium on Computers and Communications
ISSN (Print)1530-1346
ISSN (Electronic)2642-7389

Conference

Conference IEEE Symposium on Computers and Communications
Country/TerritoryGreece
Period5/09/218/09/21

Keywords

  • Training
  • Computers
  • Privacy
  • Data privacy
  • Computational modeling
  • Machine learning
  • Data models
  • Neural Networks
  • Homomorphic Encryption
  • Polynomial Approximation
  • Activation Functions

Publication forum classification

  • Publication forum level 1

Fingerprint

Dive into the research topics of 'Blind Faith: Privacy-Preserving Machine Learning using Function Approximation'. Together they form a unique fingerprint.

Cite this