Blockchain-Assisted Privacy And Security Enhancement In Federated Learning
DOI:
https://doi.org/10.63665/yhfhsb57Keywords:
Federated Learning, Blockchain, Homomorphic Encryption, Privacy Preservation, Byzantine-robust Aggregation, Secure Aggregation, Machine Learning, Data Security, Distributed Systems.Abstract
Federated Learning (FL) enables multiple clients to collaboratively train machine learning models without sharing raw data, thereby enhancing data privacy and security. However, traditional federated learning systems remain vulnerable to privacy leakage, poisoning attacks, and centralized server failures. To address these challenges, this project proposes a Blockchain-based Privacy-preserving and Secure Federated Learning (BPS-FL) framework. The proposed framework integrates threshold Paillier homomorphic encryption to achieve secure gradient aggregation while preserving client privacy. In addition, blockchain technology is incorporated to provide decentralized, transparent, and tamper-proof record management. A Byzantine-robust aggregation mechanism is also introduced to identify and mitigate malicious gradient updates without compromising data confidentiality. The proposed BPS-FL framework improves security, transparency, robustness, and trustworthiness in distributed learning environments while maintaining reliable model performance and scalability.
Downloads
References
1) L. Peng et al., “Federated Graph Learning with Network Inpainting for Population-Based Disease Prediction,” 2023.
2) R. Zhao et al., “Semi-supervised Federated-learning-based Intrusion Detection Method for IoT,” 2023.
3) X. Gong et al., “Backdoor Attacks and Defenses in Federated Learning,” 2023.
4) X. Ma et al., “Differentially Private Byzantine-robust Federated Learning,” 2022.
5) L. Zhao et al., “Secure and Efficient Aggregation for Byzantine-robust Federated Learning,” 2022.
6) Y. Dong et al., “Oblivious Defender for Private Byzantine-robust Federated Learning,” 2021.
7) X. Liu et al., “Privacy-enhanced Federated Learning against Poisoning Adversaries,” 2021.
8) Y. Li et al., “Privacy-preserving Federated Learning Framework based on Chained Secure Multiparty Computing,” 2021.
9) J. H. Bell et al., “Secure Single-server Aggregation with Polylogarithmic Overhead,” 2020.
10) Y. Li et al., “Toward Secure and Privacy-preserving Distributed Deep Learning in Fog-cloud Computing,” 2020.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Authors
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
