Generic selectors
Exact matches only
Search in title
Search in content
Post Type Selectors

TFKAN: Transformer based on Kolmogorov–Arnold Networks for Intrusion Detection in IoT environment

Item Details
Title TFKAN: Transformer based on Kolmogorov–Arnold Networks for Intrusion Detection in IoT environment
Authors Ibrahim . Fares , Mohamed Abd Elaziz , Ahmad . Aseeri , Hamed Shawky Zied , Ahmed . Abdellatif
Journal Name Egyptian Informatics Journal
Issue Number "2090-4754 1110-8665"
Pages From 2090 to 8665
Publication Year 2025
DOI https://doi.org/10.1016/j.eij.2025.100666
Abstract
This work proposes a novel Transformer based on the Kolmogorov–Arnold Network (TFKAN) model for Intrusion Detection Systems (IDS) in the IoT environment. The TFKAN Transformer is developed by implementing the Kolmogorov–Arnold Networks (KANs) layers instead of the Multi-Layer Perceptrons (MLP) layers. Unlike the MLPs feed-forward layer, KAN layers have no fixed weights but use learnable univariate function components, enabling a more compact representation. This means a KAN can achieve comparable performance with fewer trainable parameters than a larger MLP. The RT-IoT2022, IoT23, and CICIoT2023 datasets were used in the evaluation process. The proposed TFKAN Transformer outperforms and obtains higher accuracy scores of 99.96%, 98.43%, and 99.27% on the RT-IoT2022, IoT23, and CICIoT2023 datasets, respectively. The results indicate that the developed Transformer using KAN shows promising performance in IDS within IoT environments compared to MLP layers.Transformers based on KANs are on average 78% lighter, in parameter count, than Transformers using MLPs. This makes KANs promising to be a replacement for MLPs.
Leave a Reply

Your email address will not be published. Required fields are marked *