Secure Logistic Regression for Vertical Federated Learning

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review

View graph of relations

Author(s)

  • Daojing He
  • Runmeng Du
  • Shanshan Zhu
  • Min Zhang
  • Kaitai Liang

Related Research Unit(s)

Detail(s)

Original languageEnglish
Pages (from-to)61-68
Journal / PublicationIEEE Internet Computing
Volume26
Issue number2
Online published28 Dec 2021
Publication statusPublished - Mar 2022

Abstract

Data island effectively blocks the practical application of machine learning. To meet this challenge, a new framework known as Federated Learning (FL) was born. It allows model training on a large amount of scattered data owned by different data providers. This paper presents a parallel solution for computing logistic regression based on distributed asynchronous task framework. Compared to the existing work, our proposed solution does not rely on any third party coordinator, and hence has better security and can solve the multi-training problem. The logistic regression based on homomorphic encryption is implemented in Python, which is used for vertical federated learning and prediction of the resulting model. We evaluate the proposed solution using the MNIST data set, and the experimental results show that good performance is achieved.

Research Area(s)

  • Collaborative work, Computational modeling, Data models, Federated learning, homomorphic encryption, logistic regression, Logistics, multiparty privacy computation, Protocols, Security, Training

Citation Format(s)

Secure Logistic Regression for Vertical Federated Learning. / He, Daojing; Du, Runmeng; Zhu, Shanshan; Zhang, Min; Liang, Kaitai; Chan, Sammy.

In: IEEE Internet Computing, Vol. 26, No. 2, 03.2022, p. 61-68.

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journalpeer-review