A privacy-preserving federated learning framework for blockchain networks

Authors

Youssif Abuzied, The American University in Cairo
Mohamed Ghanem, The American University in Cairo
Fadi Dawoud, The American University in Cairo
Habiba Gamal, The American University in Cairo
Eslam Soliman, The American University in Cairo
Hossam Sharara, The American University in Cairo
Tamer ElBatt, The American University in Cairo

Author's Department

Computer Science & Engineering Department

Second Author's Department

Computer Science & Engineering Department

Third Author's Department

Computer Science & Engineering Department

Fourth Author's Department

Computer Science & Engineering Department

Fifth Author's Department

Computer Science & Engineering Department

Find in your Library

https://doi.org/10.1007/s10586-024-04273-1

All Authors

Youssif Abuzied, Mohamed Ghanem, Fadi Dawoud, Habiba Gamal, Eslam Soliman, Hossam Sharara, Tamer ElBatt

Document Type

Research Article

Publication Title

Cluster Computing

Publication Date

7-1-2024

doi

10.1007/s10586-024-04273-1

Abstract

In this paper we introduce a scalable, privacy-preserving, federated learning framework, coined FLoBC, based on the concept of distributed ledgers underlying blockchains. This is motivated by the rapid growth of data worldwide, especially decentralized data which calls for scalable, decenteralized machine learning models which is capable of preserving the privacy of the data of the participating users. Towards this objective, we first motivate and define the problem scope. We then introduce the proposed FLoBC system architecture hinging on a number of key pillars, namely parallelism, decentralization and node update synchronization. In particular, we examine a number of known node update synchronization policies and examine their performance merits and design trade-offs. Finally, we compare the proposed federated learning system to a centralized learning system baseline to demonstrate its performance merits. Our main finding in this paper is that our proposed decentralized learning framework was able to achieve comparable performance to a classic centralized learning system, while distributing the model training process across multiple nodes without sharing their actual data. This provides a scalable, privacy-preserving solution for training a variety of large machine learning models. Graphical abstract: (Figure presented.)

First Page

3997

Last Page

4014

Comments

Article. Record derived from SCOPUS.

Recommended Citation

APA Citation

Abuzied, Y. Ghanem, M. Dawoud, F. Gamal, H. ... (2024). A privacy-preserving federated learning framework for blockchain networks. Cluster Computing, 27(4), 3997–4014. https://doi.org/10.1007/s10586-024-04273-1

MLA Citation

Abuzied, Youssif, et al. "A privacy-preserving federated learning framework for blockchain networks." Cluster Computing, vol. 27, no. 4, 2024, pp. 3997–4014.
https://doi.org/10.1007/s10586-024-04273-1