Federated learning for intrusion detection in IoT security: a hybrid ensemble approach
Sayan Chatterjee, Manjesh K. Hanawal
Abstract
Critical role of the internet of things (IoT) in various domains like smart city, healthcare, supply chain, and transportation has made them the target of malicious attacks. Past works in this area focused on centralised intrusion detection system (IDS), assuming a central entity to perform data analysis and identify threats. However, such IDS may not always be feasible, mainly due to the spread of data across multiple sources, and gathering at a central node can be costly. In this paper, we first present an architecture for IDS based on a hybrid ensemble model named PHEC, which gives improved performance compared to state-of-the-art architectures. We then adapt this model to a federated learning framework. Next, we propose noise-tolerant PHEC to address the label-noise problem. Experimental results on four benchmark datasets drawn from various security attacks show that our model achieves high TPR while keeping FPR low on noisy and clean data.