Enhancing Intrusion Detection in IoT Environments: An Advanced Ensemble Approach Using Kolmogorov-Arnold Networks

TL;DR

This paper tackles intrusion detection in IoT networks by introducing a hybrid IDS that fuses Kolmogorov-Arnold Networks (KANs) with XGBoost to model complex traffic patterns. The KAN provides learnable activation functions within a layered representation, while XGBoost contributes scalable, high-performance classification, resulting in a robust detector. On the N-BaIoT dataset, the KAN-XGBoost system achieves accuracy around 99.69% with precision, recall, and F1 scores above 98%, outperforming both MLP and KAN baselines. The approach offers strong detection performance and interpretability, representing the first application of KANs to intrusion detection and promising enhanced security for dynamic IoT environments.

Abstract

In recent years, the evolution of machine learning techniques has significantly impacted the field of intrusion detection, particularly within the context of the Internet of Things (IoT). As IoT networks expand, the need for robust security measures to counteract potential threats has become increasingly critical. This paper introduces a hybrid Intrusion Detection System (IDS) that synergistically combines Kolmogorov-Arnold Networks (KANs) with the XGBoost algorithm. Our proposed IDS leverages the unique capabilities of KANs, which utilize learnable activation functions to model complex relationships within data, alongside the powerful ensemble learning techniques of XGBoost, known for its high performance in classification tasks. This hybrid approach not only enhances the detection accuracy but also improves the interpretability of the model, making it suitable for dynamic and intricate IoT environments. Experimental evaluations demonstrate that our hybrid IDS achieves an impressive detection accuracy exceeding 99% in distinguishing between benign and malicious activities. Additionally, we were able to achieve F1 scores, precision, and recall that exceeded 98%. Furthermore, we conduct a comparative analysis against traditional Multi-Layer Perceptron (MLP) networks, assessing performance metrics such as Precision, Recall, and F1-score. The results underscore the efficacy of integrating KANs with XGBoost, highlighting the potential of this innovative approach to significantly strengthen the security framework of IoT networks.

Figures (5)

• Figure 1: A basic structure for KANS liu2024kan
• Figure 2: A summary of the original N-BaIoT dataset instances per device(dataset) and per attack (class).
• Figure 3: Number of samples per class (Benign or Malicious) used in the experiments' dataset
• Figure 4: Confusion matrix for the proposed KAN-XGBoost scheme
• Figure 5: Epoch count vs loss for KAN, MLP, and KAN-XGBoost, the lower part is from epoch 5 to epoch 50.