Reliability check via weight similarity in privacy-preserving multi-party machine learning

Kennedy Edemacu, Beakcheol Jang, Jong Wook Kim

Research output: Contribution to journalArticlepeer-review

2 Citations (Scopus)


Multi-party machine learning is a paradigm in which multiple participants collaboratively train a machine learning model to achieve a common learning objective without sharing their privately owned data. The paradigm has recently received a lot of attention from the research community aimed at addressing its associated privacy concerns. In this work, we focus on addressing the concerns of data privacy, model privacy, and data quality associated with privacy-preserving multi-party machine learning, i.e., we present a scheme for privacy-preserving collaborative learning that checks the participants’ data quality while guaranteeing data and model privacy. In particular, we propose a novel metric called weight similarity that is securely computed and used to check whether a participant can be categorized as a reliable participant (holds good quality data) or not. The problems of model and data privacy are tackled by integrating homomorphic encryption in our scheme and uploading encrypted weights, which prevent leakages to the server and malicious participants, respectively. The analytical and experimental evaluations of our scheme demonstrate that it is accurate and ensures data and model privacy.

Original languageEnglish
Pages (from-to)51-65
Number of pages15
JournalInformation sciences
Publication statusPublished - 2021 Oct

Bibliographical note

Funding Information:
We thank the anonymous reviewers for their constructive comments that have led to the improved quality of this work.

Publisher Copyright:
© 2021 Elsevier Inc.

All Science Journal Classification (ASJC) codes

  • Software
  • Control and Systems Engineering
  • Theoretical Computer Science
  • Computer Science Applications
  • Information Systems and Management
  • Artificial Intelligence


Dive into the research topics of 'Reliability check via weight similarity in privacy-preserving multi-party machine learning'. Together they form a unique fingerprint.

Cite this