An intrusion detection model based on Convolutional Kolmogorov-Arnold Networks
Abstract The application of artificial neural networks (ANNs) can be found in numerous fields, including image and speech recognition, natural language processing, and autonomous vehicles. As well, intrusion detection, the subject of this paper, relies heavily on it. Different intrusion detection mo...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-85083-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832594713816858624 |
|---|---|
| author | Zhen Wang Anazida Zainal Maheyzah Md Siraj Fuad A. Ghaleb Xue Hao Shaoyong Han |
| author_facet | Zhen Wang Anazida Zainal Maheyzah Md Siraj Fuad A. Ghaleb Xue Hao Shaoyong Han |
| author_sort | Zhen Wang |
| collection | DOAJ |
| description | Abstract The application of artificial neural networks (ANNs) can be found in numerous fields, including image and speech recognition, natural language processing, and autonomous vehicles. As well, intrusion detection, the subject of this paper, relies heavily on it. Different intrusion detection models have been constructed using ANNs. While ANNs are relatively mature to construct intrusion detection models, some challenges remain. Among the most notorious of these are the bloated models caused by the large number of parameters, and the non-interpretability of the models. Our paper presents Convolutional Kolmogorov-Arnold Networks (CKANs), which are designed to overcome these difficulties and provide an interpretable and accurate intrusion detection model. Kolmogorov-Arnold Networks (KANs) are developed from the Kolmogorov-Arnold representation theorem. Meanwhile, CKAN incorporates a convolutional computational mechanism based on KAN. The model proposed in this paper is constructed by incorporating attention mechanisms into CKAN’s computational logic. The datasets CICIoT2023 and CICIoMT2024 were used for model training and validation. From the results of evaluating the performance indicators of the experiments, the intrusion detection model constructed based on CKANs has an attractive application prospect. As compared with other methods, the model can predict a much higher level of accuracy with significantly fewer parameters. However, it is not superior in terms of memory usage, execution speed and energy consumption. |
| format | Article |
| id | doaj-art-abbd0ddfd6244f3cbcc9e7f495f59722 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-abbd0ddfd6244f3cbcc9e7f495f597222025-01-19T12:23:50ZengNature PortfolioScientific Reports2045-23222025-01-0115112210.1038/s41598-024-85083-8An intrusion detection model based on Convolutional Kolmogorov-Arnold NetworksZhen Wang0Anazida Zainal1Maheyzah Md Siraj2Fuad A. Ghaleb3Xue Hao4Shaoyong Han5School of Data Science and Artificial Intelligence, Wenzhou University of TechnologyFaculty of Computing, Universiti Teknologi MalaysiaFaculty of Computing, Universiti Teknologi MalaysiaCollege of Computing and Digital Technology, Birmingham City UniversityFaculty of Computing, Universiti Teknologi MalaysiaSchool of Mathematics and Computer Science, Tongling UniversityAbstract The application of artificial neural networks (ANNs) can be found in numerous fields, including image and speech recognition, natural language processing, and autonomous vehicles. As well, intrusion detection, the subject of this paper, relies heavily on it. Different intrusion detection models have been constructed using ANNs. While ANNs are relatively mature to construct intrusion detection models, some challenges remain. Among the most notorious of these are the bloated models caused by the large number of parameters, and the non-interpretability of the models. Our paper presents Convolutional Kolmogorov-Arnold Networks (CKANs), which are designed to overcome these difficulties and provide an interpretable and accurate intrusion detection model. Kolmogorov-Arnold Networks (KANs) are developed from the Kolmogorov-Arnold representation theorem. Meanwhile, CKAN incorporates a convolutional computational mechanism based on KAN. The model proposed in this paper is constructed by incorporating attention mechanisms into CKAN’s computational logic. The datasets CICIoT2023 and CICIoMT2024 were used for model training and validation. From the results of evaluating the performance indicators of the experiments, the intrusion detection model constructed based on CKANs has an attractive application prospect. As compared with other methods, the model can predict a much higher level of accuracy with significantly fewer parameters. However, it is not superior in terms of memory usage, execution speed and energy consumption.https://doi.org/10.1038/s41598-024-85083-8Kolmogorov-Arnold NetworksConvolutional neural networkIntrusion detectionDeep learningArtificial intelligence |
| spellingShingle | Zhen Wang Anazida Zainal Maheyzah Md Siraj Fuad A. Ghaleb Xue Hao Shaoyong Han An intrusion detection model based on Convolutional Kolmogorov-Arnold Networks Scientific Reports Kolmogorov-Arnold Networks Convolutional neural network Intrusion detection Deep learning Artificial intelligence |
| title | An intrusion detection model based on Convolutional Kolmogorov-Arnold Networks |
| title_full | An intrusion detection model based on Convolutional Kolmogorov-Arnold Networks |
| title_fullStr | An intrusion detection model based on Convolutional Kolmogorov-Arnold Networks |
| title_full_unstemmed | An intrusion detection model based on Convolutional Kolmogorov-Arnold Networks |
| title_short | An intrusion detection model based on Convolutional Kolmogorov-Arnold Networks |
| title_sort | intrusion detection model based on convolutional kolmogorov arnold networks |
| topic | Kolmogorov-Arnold Networks Convolutional neural network Intrusion detection Deep learning Artificial intelligence |
| url | https://doi.org/10.1038/s41598-024-85083-8 |
| work_keys_str_mv | AT zhenwang anintrusiondetectionmodelbasedonconvolutionalkolmogorovarnoldnetworks AT anazidazainal anintrusiondetectionmodelbasedonconvolutionalkolmogorovarnoldnetworks AT maheyzahmdsiraj anintrusiondetectionmodelbasedonconvolutionalkolmogorovarnoldnetworks AT fuadaghaleb anintrusiondetectionmodelbasedonconvolutionalkolmogorovarnoldnetworks AT xuehao anintrusiondetectionmodelbasedonconvolutionalkolmogorovarnoldnetworks AT shaoyonghan anintrusiondetectionmodelbasedonconvolutionalkolmogorovarnoldnetworks AT zhenwang intrusiondetectionmodelbasedonconvolutionalkolmogorovarnoldnetworks AT anazidazainal intrusiondetectionmodelbasedonconvolutionalkolmogorovarnoldnetworks AT maheyzahmdsiraj intrusiondetectionmodelbasedonconvolutionalkolmogorovarnoldnetworks AT fuadaghaleb intrusiondetectionmodelbasedonconvolutionalkolmogorovarnoldnetworks AT xuehao intrusiondetectionmodelbasedonconvolutionalkolmogorovarnoldnetworks AT shaoyonghan intrusiondetectionmodelbasedonconvolutionalkolmogorovarnoldnetworks |