Robust Blockchained Federated Learning with Model Validation and Proof-of-Stake Inspired Consensus
This work provides a more robust federated learning framework for distributed machine learning systems by mitigating the impact of malicious devices and single points of failure.
This paper addresses the robustness issues in federated learning (FL) by proposing VBFL, a blockchain-based decentralized framework. It introduces a decentralized validation mechanism for local model updates and a proof-of-stake consensus that rewards honest devices. With 15% malicious devices, VBFL achieves 87% accuracy, which is 7.4x higher than Vanilla FL.
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.