Deep Transfer Learning Based on Hybrid Swin Transformers With LSTM for Intrusion Detection Systems in IoT Environment
Extensive growth in the number of Internet Of Things (IoT) devices has significantly increased susceptibility to various cyber-attacks and hence emphasized the need for robust intrusion detection systems (IDS) for ensuring IoT network security. While deep learning (DL) methodologies have proven effe...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Open Journal of the Communications Society |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11005405/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850161426141806592 |
|---|---|
| author | Ibrahim A. Fares Ahmed Gamal Abdellatif Ibrahim Mohamed Abd Elaziz Mansour Shrahili Adham Ahmed Elmahallawy Rana Muhammad Sohaib Mahmoud A. Shawky Syed Tariq Shah |
| author_facet | Ibrahim A. Fares Ahmed Gamal Abdellatif Ibrahim Mohamed Abd Elaziz Mansour Shrahili Adham Ahmed Elmahallawy Rana Muhammad Sohaib Mahmoud A. Shawky Syed Tariq Shah |
| author_sort | Ibrahim A. Fares |
| collection | DOAJ |
| description | Extensive growth in the number of Internet Of Things (IoT) devices has significantly increased susceptibility to various cyber-attacks and hence emphasized the need for robust intrusion detection systems (IDS) for ensuring IoT network security. While deep learning (DL) methodologies have proven effective in the application of IDS, their success greatly depends on the availability of large datasets and significant computational resources during training. To overcome the limitations associated with this dependence on large datasets and significant computational capacity for training, the current work suggests employing the transfer learning (TL) mechanism by combining Swin Transformers with long short-term memory (LSTM) networks. Utilizing the beneficial properties of Swin Transformers in learning hierarchically structured data combined with the proficiency of LSTM in processing sequential dependencies, the hybrid model generates pre-trained weights in the first phase. These pre-trained weights are further transferred into another instance of the new model for subsequent fine-tuning. Experiments are carried out on several benchmarking datasets, namely NSL-KDD, ToN-IoT, BoTIoT, MQTTIoT, and CICIoT2023, which include both binary and multi-class classification scenarios. The proposed model outperforms state-of-the-art DL models, for example, the Autoencoders, ResNets, CNN, RNN, and LSTM models, and achieved an average of 98.97% in accuracy, of 98.97% in precision, of 99.02% in recall, of 98.97% in F1 score, across all datasets. Experimental results establish that the hybrid approach achieves better detection accuracy and better performance measures compared to the latest state-of-the-art methods, thus proving itself effective in increasing the scalability and adaptability of IDS in IoT. |
| format | Article |
| id | doaj-art-d3adb1d4c6dc4f3e94a9cc1a8c4a0b6a |
| institution | OA Journals |
| issn | 2644-125X |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Open Journal of the Communications Society |
| spelling | doaj-art-d3adb1d4c6dc4f3e94a9cc1a8c4a0b6a2025-08-20T02:22:50ZengIEEEIEEE Open Journal of the Communications Society2644-125X2025-01-0164342436510.1109/OJCOMS.2025.356930111005405Deep Transfer Learning Based on Hybrid Swin Transformers With LSTM for Intrusion Detection Systems in IoT EnvironmentIbrahim A. Fares0https://orcid.org/0000-0002-2732-7850Ahmed Gamal Abdellatif Ibrahim1https://orcid.org/0000-0002-3440-8448Mohamed Abd Elaziz2https://orcid.org/0000-0002-7682-6269Mansour Shrahili3https://orcid.org/0000-0003-3456-8393Adham Ahmed Elmahallawy4Rana Muhammad Sohaib5Mahmoud A. Shawky6https://orcid.org/0000-0003-3393-8460Syed Tariq Shah7https://orcid.org/0000-0003-4722-1786Department of Mathematics, Faculty of Science, Zagazig University, Zagazig, EgyptDepartment of Electronics and Electrical Engineering, ADC EMA, Cairo, EgyptDepartment of Mathematics, Faculty of Science, Zagazig University, Zagazig, EgyptDepartment of Statistics and Operations Research, College of Science, King Saud University, Riyadh, Saudi ArabiaHigher Institute of Engineering and Technology, King Mariout, Alexandria, EgyptDepartment of Computer and Information Science, Northumbria University, Newcastle upon Tyne, U.K.Department of Electronics and Electrical Engineering, ADC EMA, Cairo, EgyptSchool of Computer Science and Electronic Engineering, University of Essex, Colchester, U.K.Extensive growth in the number of Internet Of Things (IoT) devices has significantly increased susceptibility to various cyber-attacks and hence emphasized the need for robust intrusion detection systems (IDS) for ensuring IoT network security. While deep learning (DL) methodologies have proven effective in the application of IDS, their success greatly depends on the availability of large datasets and significant computational resources during training. To overcome the limitations associated with this dependence on large datasets and significant computational capacity for training, the current work suggests employing the transfer learning (TL) mechanism by combining Swin Transformers with long short-term memory (LSTM) networks. Utilizing the beneficial properties of Swin Transformers in learning hierarchically structured data combined with the proficiency of LSTM in processing sequential dependencies, the hybrid model generates pre-trained weights in the first phase. These pre-trained weights are further transferred into another instance of the new model for subsequent fine-tuning. Experiments are carried out on several benchmarking datasets, namely NSL-KDD, ToN-IoT, BoTIoT, MQTTIoT, and CICIoT2023, which include both binary and multi-class classification scenarios. The proposed model outperforms state-of-the-art DL models, for example, the Autoencoders, ResNets, CNN, RNN, and LSTM models, and achieved an average of 98.97% in accuracy, of 98.97% in precision, of 99.02% in recall, of 98.97% in F1 score, across all datasets. Experimental results establish that the hybrid approach achieves better detection accuracy and better performance measures compared to the latest state-of-the-art methods, thus proving itself effective in increasing the scalability and adaptability of IDS in IoT.https://ieeexplore.ieee.org/document/11005405/Cyber-securityintrusion detection system (IDS)IoTtransformerstransfer learning |
| spellingShingle | Ibrahim A. Fares Ahmed Gamal Abdellatif Ibrahim Mohamed Abd Elaziz Mansour Shrahili Adham Ahmed Elmahallawy Rana Muhammad Sohaib Mahmoud A. Shawky Syed Tariq Shah Deep Transfer Learning Based on Hybrid Swin Transformers With LSTM for Intrusion Detection Systems in IoT Environment IEEE Open Journal of the Communications Society Cyber-security intrusion detection system (IDS) IoT transformers transfer learning |
| title | Deep Transfer Learning Based on Hybrid Swin Transformers With LSTM for Intrusion Detection Systems in IoT Environment |
| title_full | Deep Transfer Learning Based on Hybrid Swin Transformers With LSTM for Intrusion Detection Systems in IoT Environment |
| title_fullStr | Deep Transfer Learning Based on Hybrid Swin Transformers With LSTM for Intrusion Detection Systems in IoT Environment |
| title_full_unstemmed | Deep Transfer Learning Based on Hybrid Swin Transformers With LSTM for Intrusion Detection Systems in IoT Environment |
| title_short | Deep Transfer Learning Based on Hybrid Swin Transformers With LSTM for Intrusion Detection Systems in IoT Environment |
| title_sort | deep transfer learning based on hybrid swin transformers with lstm for intrusion detection systems in iot environment |
| topic | Cyber-security intrusion detection system (IDS) IoT transformers transfer learning |
| url | https://ieeexplore.ieee.org/document/11005405/ |
| work_keys_str_mv | AT ibrahimafares deeptransferlearningbasedonhybridswintransformerswithlstmforintrusiondetectionsystemsiniotenvironment AT ahmedgamalabdellatifibrahim deeptransferlearningbasedonhybridswintransformerswithlstmforintrusiondetectionsystemsiniotenvironment AT mohamedabdelaziz deeptransferlearningbasedonhybridswintransformerswithlstmforintrusiondetectionsystemsiniotenvironment AT mansourshrahili deeptransferlearningbasedonhybridswintransformerswithlstmforintrusiondetectionsystemsiniotenvironment AT adhamahmedelmahallawy deeptransferlearningbasedonhybridswintransformerswithlstmforintrusiondetectionsystemsiniotenvironment AT ranamuhammadsohaib deeptransferlearningbasedonhybridswintransformerswithlstmforintrusiondetectionsystemsiniotenvironment AT mahmoudashawky deeptransferlearningbasedonhybridswintransformerswithlstmforintrusiondetectionsystemsiniotenvironment AT syedtariqshah deeptransferlearningbasedonhybridswintransformerswithlstmforintrusiondetectionsystemsiniotenvironment |