English

Robust Blockchained Federated Learning with Model Validation and Proof-of-Stake Inspired Consensus

Machine Learning 2021-01-12 v1 Artificial Intelligence Cryptography and Security Distributed, Parallel, and Cluster Computing Networking and Internet Architecture

Abstract

Federated learning (FL) is a promising distributed learning solution that only exchanges model parameters without revealing raw data. However, the centralized architecture of FL is vulnerable to the single point of failure. In addition, FL does not examine the legitimacy of local models, so even a small fraction of malicious devices can disrupt global training. To resolve these robustness issues of FL, in this paper, we propose a blockchain-based decentralized FL framework, termed VBFL, by exploiting two mechanisms in a blockchained architecture. First, we introduced a novel decentralized validation mechanism such that the legitimacy of local model updates is examined by individual validators. Second, we designed a dedicated proof-of-stake consensus mechanism where stake is more frequently rewarded to honest devices, which protects the legitimate local model updates by increasing their chances of dictating the blocks appended to the blockchain. Together, these solutions promote more federation within legitimate devices, enabling robust FL. Our emulation results of the MNIST classification corroborate that with 15% of malicious devices, VBFL achieves 87% accuracy, which is 7.4x higher than Vanilla FL.

Keywords

Cite

@article{arxiv.2101.03300,
  title  = {Robust Blockchained Federated Learning with Model Validation and Proof-of-Stake Inspired Consensus},
  author = {Hang Chen and Syed Ali Asif and Jihong Park and Chien-Chung Shen and Mehdi Bennis},
  journal= {arXiv preprint arXiv:2101.03300},
  year   = {2021}
}

Comments

8 pages, 7 figures, AAAI 2021 Workshop - Towards Robust, Secure and Efficient Machine Learning

R2 v1 2026-06-23T21:56:31.475Z