Attention-Based Interpretable Semi-Supervised Federated Learning for Intrusion Detection in IoT Wireless Networks
Thai Vu Nguyen, Long Bao Le · 2023
Intrusion detection is a crucial task to ensure the security of the Internet of Things (IoT) wireless networks. While different Machine Learning (ML) methods have been leveraged to detect network intrusion, they often require data from multiple devices to be collected and stored on a central server to train underlying ML models, raising privacy concerns. Federated Learning (FL) can preserve data privacy where local devices can iteratively update the model parameters trained by using their own local datasets and send them to a server for model ag-gregation. Moreover, most existing ML-based intrusion detection designs are based on supervised ML using labeled data, which may not be available or time-consuming to build. Therefore, semi-supervised learning methods that effectively utilize both labeled and unlabeled data would be very desirable and necessary. This paper proposes a semi-supervised FL method for intrusion detection in IoT networks. Specifically, our proposed framework leverages the attention-based architecture called TabNet to selec-tively focus on important features of network flow and we propose a crucial data preparation procedure before training the ML model using the FL approach. We conduct extensive numerical studies to demonstrate the effectiveness of our approach and compare its performance to other baselines. We also present empirical evidence to support the interpretability of our method. We also show that the proposed data pre-processing procedure indeed greatly enhances the intrusion detection performance.1