Skip to main navigation Skip to search Skip to main content

SFPDML: Securer and Faster Privacy-Preserving Distributed Machine Learning Based on MKTFHE

  • Hongxiao Wang
  • , Zoe L. Jiang
  • , Yanmin Zhao
  • , Siu Ming Yiu*
  • , Peng Yang
  • , Man Chen
  • , Zejiu Tan
  • , Bohan Jin
  • *Corresponding author for this work
  • The University of Hong Kong
  • School of Computer Science and Technology, Harbin Institute of Technology
  • Peng Cheng Laboratory
  • Shandong University

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

Abstract

In recent years, distributed machine learning has garnered significant attention. However, privacy continues to be an unresolved issue within this field. Multi-key homomorphic encryption over torus (MKTFHE) is one of the promising candidates for addressing this concern. Nevertheless, there may be security risks in the decryption of MKTFHE. Moreover, to our best known, the latest works about MKTFHE only support Boolean operation and linear operation which cannot directly compute the non-linear function like Sigmoid. Therefore, it’s still hard to perform common machine learning such as logistic regression and neural networks in high performance. In this paper, we first discover a possible attack on the existing distributed decryption protocol for MKTFHE and subsequently introduce secret sharing to propose a securer one. Next, we design some tools to implement logistic regression and neural network training in MKTFHE. Comparing the efficiency and accuracy between using Taylor polynomials of Sigmoid and our proposed function as an activation function, the experiments show that the efficiency of our function is 5-10× higher than using Taylor polynomials straightly and keeping a similar accuracy.

Original languageEnglish
Title of host publicationMobile Internet Security - 7th International Conference, MobiSec 2023, Revised Selected Papers
EditorsIlsun You, Hwankuk Kim, Michal Choras, Seonghan Shin, Philip Virgil Astillo
PublisherSpringer Science and Business Media Deutschland GmbH
Pages94-108
Number of pages15
ISBN (Print)9789819744640
DOIs
StatePublished - 2024
Externally publishedYes
Event7th International Conference on Mobile Internet Security, MobiSec 2023 - Okinawa, Japan
Duration: 19 Dec 202321 Dec 2023

Publication series

NameCommunications in Computer and Information Science
Volume2095 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference7th International Conference on Mobile Internet Security, MobiSec 2023
Country/TerritoryJapan
CityOkinawa
Period19/12/2321/12/23

Keywords

  • Distributed machine learning
  • Multi-key decryption
  • Multi-key fully homomorphic encryption
  • Privacy-preserving machine learning

Fingerprint

Dive into the research topics of 'SFPDML: Securer and Faster Privacy-Preserving Distributed Machine Learning Based on MKTFHE'. Together they form a unique fingerprint.

Cite this