LiteChain: A Lightweight Blockchain for Verifiable and Scalable Federated Learning in Massive Edge Networks

2025-03-01

IEEE Transactions on Mobile Computing

AI Summary

To address the challenges of blockchain deployment difficulty, lack of standardized security evaluation, unverifiable and non-scalable collaborative training in federated learning (FL), and poor scalability in large-scale edge networks, this paper proposes a lightweight blockchain framework. Methodologically, it designs a distributed two-tier clustering network architecture; introduces a novel Composite Byzantine Fault Tolerance (CBFT) consensus mechanism; and builds a Hyperledger Fabric–based on-chain model update and verification system, integrating replay- and poisoning-resistant model validation. Contributions include: (i) establishing the first quantitative security evaluation paradigm for FL-oriented blockchains; (ii) achieving high robustness at thousand-node scale; (iii) attaining state-of-the-art end-to-end latency and on-chain storage overhead; and (iv) significantly enhancing security, verifiability, and scalability of edge-based FL systems.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Natural Language Processing: Safety and Robustness
• Data Mining & Knowledge Management: Scalability, Parallel & Distributed Systems

Application Category

• Security and Privacy: Blockchains and distributed ledgers
• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Economics, Online Markets and Human Computation: Economic aspects of blockchain and cryptocurrencies

Abstract

Leveraging blockchain in Federated Learning (FL) emerges as a new paradigm for secure collaborative learning on Massive Edge Networks (MENs). As the scale of MENs increases, it becomes more difficult to implement and manage a blockchain among edge devices due to complex communication topologies, heterogeneous computation capabilities, and limited storage capacities. Moreover, the lack of a standard metric for blockchain security becomes a significant issue. To address these challenges, we propose a lightweight blockchain for verifiable and scalable FL, namely LiteChain, to provide efficient and secure services in MENs. Specifically, we develop a distributed clustering algorithm to reorganize MENs into a two-level structure to improve communication and computing efficiency under security requirements. Moreover, we introduce a Comprehensive Byzantine Fault Tolerance (CBFT) consensus mechanism and a secure update mechanism to ensure the security of model transactions through LiteChain. Our experiments based on Hyperledger Fabric demonstrate that LiteChain presents the lowest end-to-end latency and on-chain storage overheads across various network scales, outperforming the other two benchmarks. In addition, LiteChain exhibits a high level of robustness against replay and data poisoning attacks.

Problem

• Addresses scalability and security in Federated Learning on Massive Edge Networks.
• Proposes a lightweight blockchain for efficient and secure model transactions.
• Introduces mechanisms to improve communication and computing efficiency securely.

Innovation

• Lightweight blockchain for scalable federated learning
• Distributed clustering algorithm for efficient communication
• CBFT consensus mechanism for secure model transactions