Federated Learning Framework for IoT Intrusion Detection Using Tab Transformer and Nature-Inspired Hyper-Parameter Optimization

Ibrahim A. Fares^1*Mohamed Abd Elaziz¹Abdelghani Dahou²Mansour Shrahili³

• ¹Faculty of Science, Zagazig University, Zagazig, Egypt
• ²School of Mathematics and Computer Science, Jiangxi Science and Technology Normal University, Nanchang, Jiangxi Province, China
• ³Department of Information Science, College of Arts, King Saud University, Riyadh, Saudi Arabia

Intrusion detection has been of prime concern in the IoT environment due to the rapid increase in cyber threats. Most traditional Intrusion Detection Systems (IDSs) rely on centralized models, raising significant privacy concerns. Federated Learning (FL) offers a decentralized alternative; however, many existing FL-based IDS frameworks suffer from poor performance due to suboptimal model architectures and ineffective hyper-parameter selection. To address these challenges, this paper introduces a novel trust-centric FL framework for IDS based on the Tab Transformer model. We enhance the Tab model through an optimization process, utilizing a hyper-parameter tuning algorithm inspired by the nature-based Electric Eel Foraging Optimization (EEFO) algorithm. The goal of the developed framework is to improve the detection of IDS without using centralized data to preserve privacy. Whereas it enhances the processing and detection capability of the huge amounts of data generated from Internet of Things (IoT) devices. Our framework is tested on three IoT datasets: N-BaIoT, UNSW-NB15, and CICIoT2023 to ensure the performance of the model. Experimental results show that the proposed framework significantly exceeds traditional methods in terms of accuracy, precision, and recall. The results presented in this study confirm the effectiveness and superior performance of the proposed FL-based IDS framework.