A Trust-Centric Federated Edge Learning Paradigm in Healthcare for Decentralized Threat Intelligence Sharing

Abstract

Growing adoption of consumer applications powered by edge intelligence and federated learning (FL) enables real-time personalization and rapid cyber response. The conventional FL remains vulnerable to adversarial attacks and lacks secure mechanism for collaborative intelligence sharing. To address this, the blockchain-enhanced FL framework that integrates decentralized model training with blockchain based threat intelligence exchange is proposed. Edge (IoT) devices collaboratively train lightweight FL models for localized detection, while blockchain ensure secure validation and dissemination on updates. A dynamic trust scoring system identifies and penalizes the malicious participants, thereby improving model reliability and resilience. Experimental results demonstrate that the proposed system has secured an accuracy of 92.8%, reduces communication overhead by 35% and maintain stable convergence across heterogeneous edge-IoT environments.