Abstract

With the blooming of machine learning, Distributed Collaborative Machine Learning (DCML) approaches have been used in various applications to scale up the training process. However, they may have privacy issues that need to be addressed. Split learning is one of the latest DCML approaches that enable the training of the machine learning models without sharing the raw data. In this paper, we study the novel problem of building a privacy-preserving text classifier in the split learning setting. This task, however, is challenging due to the need to maintain the utility of the text data for downstream tasks while protecting privacy by preventing the leakage of private attributes. We address this dilemma of privacy and utility in this work. We propose a text classification for split learning, PPSL, which utilizes the adversarial learning to minimize the private attribute leakage. We study the impacts of increasing the training time and the number of hidden layers on the privacy of split learning. Our experimental results demonstrate the effectiveness of the proposed framework that retains the sentiment meaning and preserves the private attributes while minimizing the leakage.

Original languageEnglish (US)
Title of host publicationProceedings - 2022 4th International Conference on Data Intelligence and Security, ICDIS 2022
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages160-167
Number of pages8
ISBN (Electronic)9781665459686
DOIs
StatePublished - 2022
Event4th International Conference on Data Intelligence and Security, ICDIS 2022 - Shenzhen, China
Duration: Aug 24 2022Aug 26 2022

Publication series

NameProceedings - 2022 4th International Conference on Data Intelligence and Security, ICDIS 2022

Conference

Conference4th International Conference on Data Intelligence and Security, ICDIS 2022
Country/TerritoryChina
CityShenzhen
Period8/24/228/26/22

Keywords

  • adversarial learning
  • privacy
  • split learning
  • text

ASJC Scopus subject areas

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

Fingerprint

Dive into the research topics of 'PPSL: Privacy-Preserving Text Classification for Split Learning'. Together they form a unique fingerprint.

Cite this