article · IEEE Access
A Convolutional Kolmogorov-Arnold Network architecture has been created to detect cyber intrusions in Internet of Things environments. The design alters standard Convolutional Neural Networks by swapping traditional Multi-Layer Perceptrons for Kolmogorov-Arnold Networks, achieving superior performance with fewer parameters. In evaluations against established deep learning alternatives, including standard convolutional networks, recurrent neural networks, and autoencoders, the model demonstrated higher accuracy, precision, recall, and F1 scores across both binary and multi-class tasks. Testing across three benchmark datasets, consisting of NSL_KDD, CICIoT2023, and TONIoT, yielded binary classification accuracies between 98.71% and 99.93%, alongside multi-classification accuracies reaching up to 99.2%. The findings confirm that Kolmogorov-Arnold Networks can serve as an effective, parameter-efficient replacement for multi-layer perceptron layers in network security settings.
Connected devices face continuous cybersecurity threats, requiring reliable intrusion detection mechanisms that do not overload computational resources. Traditional deep learning approaches often demand substantial parameter processing. By cutting parameter requirements while increasing threat detection precision, this approach makes automated network monitoring more feasible for Internet of Things networks that require fast, lightweight protection.
The model provides an applied and tested algorithmic framework for cybersecurity developers and Internet of Things network administrators seeking efficient intrusion detection tools. Because it attains high detection metrics with fewer parameters, it is suited for resource-constrained network monitoring. The research represents an early, software-validated stage tested on offline benchmark datasets, meaning substantial engineering and real-world network testing remain necessary before commercial implementation.
AI-generated from the published abstract. Always read the original work before citing.
This paper proposes a novel Convolutional Kolmogorov-Arnold Network (CKAN) model for Intrusion Detection Systems (IDS) in an IoT environment. The CKAN model is developed by replacing the Multi-Layer Perceptrons (MLPs) layers with Kolmogorov-Arnold Networks (KANs) layers inside the Convolutional Neural Networks (CNN) architecture. The KANs give high performance compared to the MLPs layers with fewer parameters. The performance of the proposed CKAN model has been evaluated against other well-known Deep Learning (DL) models like CNN, recurrent neural networks (RNN), and Autoencoder. The evaluation process has been carried out with three benchmark datasets: NSL_KDD, which is treated as a standard IDS dataset; CICIoT2023; TONIoT, which are IoT IDS datasets. The results point out the superiority of the CKAN model over other DL models for both binary and multi-classification tasks as per the accuracy, precision, recall, and F1 score. The proposed CKAN model achieved accuracies of 98.71%, 99.22%, and 99.93% for binary classification, and 99.2%, 98.84%, and 93.3% for multi-classification on the NSL_KDD, CICIoT2023, and TONIoT datasets, respectively. The CKAN model gives better performance metrics with a smaller number of parameters compared to other DL models. In this way, our findings point out that KANs are promising for being a substitute for MLPs.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1109/access.2024.3462297
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
