Blockchain-Empowered Cyber-Secure Federated Learning for Trustworthy Edge Computing
Ervin Moore, Ahmed Imteaj, Md Zarif Hossain, Shabnam Rezapour, M. Hadi Amini
TL;DR
The paper addresses the poisoning vulnerabilities of Federated Learning in edge environments by proposing a blockchain-enabled cross-device FL framework that uses a decentralized reputation system, resource-aware participant selection, and token-based authenticity. It introduces an on-chain/off-chain architecture with token, aggregator, and reputation smart contracts, plus a Committee Consensus mechanism to validate updates and manage trust scores. To defend against poisoned updates and membership inference, it integrates outlier detection via Euclidean distance and K-means clustering and applies gradient obfuscation for privacy. Experimental evaluation on the NASA turbofan regression task demonstrates robustness to outliers and noise, reduced storage requirements through local blockchain strategies, and scalable participation with manageable communication overhead. This work advances secure, transparent, and efficient edge-centric FL by combining blockchain governance with robust poisoning defenses and resource-aware participation.
Abstract
Federated Learning (FL) is a privacy-preserving distributed machine learning scheme, where each participant data remains on the participating devices and only the local model generated utilizing the local computational power is transmitted throughout the database. However, the distributed computational nature of FL creates the necessity to develop a mechanism that can remotely trigger any network agents, track their activities, and prevent threats to the overall process posed by malicious participants. Particularly, the FL paradigm may become vulnerable due to an active attack from the network participants, called a poisonous attack. In such an attack, the malicious participant acts as a benign agent capable of affecting the global model quality by uploading an obfuscated poisoned local model update to the server. This paper presents a cross-device FL model that ensures trustworthiness, fairness, and authenticity in the underlying FL training process. We leverage trustworthiness by constructing a reputation-based trust model based on contributions of agents toward model convergence. We ensure fairness by identifying and removing malicious agents from the training process through an outlier detection technique. Further, we establish authenticity by generating a token for each participating device through a distributed sensing mechanism and storing that unique token in a blockchain smart contract. Further, we insert the trust scores of all agents into a blockchain and validate their reputations using various consensus mechanisms that consider the computational task.