Privacy-Preserving Deep Sequential Model with Matrix Homomorphic Encryption

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

27 Scopus citations

Abstract

Making deep neural networks available as a service introduces privacy problems, for which homomorphic encryption of both model and user data potentially offers the solution at the highest privacy level. However, the difficulty of operating on homomorphically encrypted data has hitherto limited the range of operations available and the depth of networks. We introduce an extended CKKS scheme MatHEAAN to provide efficient matrix representations and operations together with improved noise control. Using the MatHEAAN we developed a deep sequential model with a gated recurrent unit called MatHEGRU. We evaluated the proposed model using sequence modeling, regression, and classification of images and genome sequences. We show that the hidden states of the encrypted model, as well as the results, are consistent with a plaintext model.

Original languageEnglish
Title of host publicationASIA CCS 2022 - Proceedings of the 2022 ACM Asia Conference on Computer and Communications Security
PublisherAssociation for Computing Machinery, Inc
Pages377-391
Number of pages15
ISBN (Electronic)9781450391405
DOIs
StatePublished - 30 May 2022
Event17th ACM ASIA Conference on Computer and Communications Security 2022, ASIA CCS 2022 - Virtual, Online, Japan
Duration: 30 May 20223 Jun 2022

Publication series

NameASIA CCS 2022 - Proceedings of the 2022 ACM Asia Conference on Computer and Communications Security

Conference

Conference17th ACM ASIA Conference on Computer and Communications Security 2022, ASIA CCS 2022
Country/TerritoryJapan
CityVirtual, Online
Period30/05/223/06/22

Keywords

  • artificial intelligence
  • deep learning
  • homomorphic encryption
  • recurrent neural network

Fingerprint

Dive into the research topics of 'Privacy-Preserving Deep Sequential Model with Matrix Homomorphic Encryption'. Together they form a unique fingerprint.

Cite this