An Optimised Transformer-Based Intrusion Detection Framework for IoT Networks Using Fisher Score Feature Selection and SMOTE Balancing Technique
DOI:
https://doi.org/10.63561/jca.v3i1.1244Keywords:
Transformer, Fisher’s Score, SMOTE, IoT, IDSAbstract
The proliferation of Internet of Things (IoT) devices has brought about significant advantages in areas such as smart homes and industrial automation. However, this widespread adoption has also rendered these systems more susceptible to cyberattacks, underscoring the critical need for robust intrusion detection systems. The proposed model presents an optimised approach to intrusion detection in IoT networks using a transformer-based architecture, renowned for its exceptional performance across diverse machine-learning tasks. This model was validated on the BoT-IoT Network Intrusion dataset, which encompasses a variety of IoT network traffic scenarios. The Synthetic Minority Oversampling Technique (SMOTE) was leveraged to address the imbalanced dataset. Furthermore, we improved efficiency by employing Fisher's score to select the most critical features. The Transformer-based model, leveraging the self-attention mechanism, was utilised to classify network traffic as normal or malicious. Our findings demonstrate the remarkable effectiveness of this approach, yielding an accuracy rate of 99%, precision of 99%, recall of 99%, F1 score of 99%, and an Area Under the Receiver Operating Characteristic Curve (AUC) of 99%. These scores confirm that our model can accurately detect and classify intrusions with minimal to no errors.
References
Aboelwafa, M. M. N., Seddik, K. G., Eldefrawy, M. H., Gadallah, Y., & Gidlund, M. (2020). A machine-learning-based technique for false data injection attack detection in industrial IoT. IEEE Internet of Things Journal, 7(9), 8462-8470. https://doi.org/10.1109/JIOT.2020.2970501.
Alsoufi, M. A., Razak, S., Siraj, M. M., Nafea, I., Ghaleb, F. A., Saeed, F., & Nasser, M. (2021). Anomaly-based intrusion detection systems in IoT using deep learning: A systematic literature review. Applied Sciences, 11(8383). https://doi.org/[CrossRef].
Arp, D., Quiring, E., Pendlebury, F., Warnecke, A., Pierazzi, F., Wressnegger, C., Cavallaro, L., & Rieck, K. (2020). Dos and don’ts of machine learning in computer security. arXiv. https://arxiv.org/abs/2010.09470.
Ashiku, L., & Dagli, C. (2021). Network intrusion detection system using deep learning. Procedia Computer Science, 185, 239–247. https://doi.org/[CrossRef].
Axelsson, S. (2019). Intrusion detection systems: A survey and taxonomy.
Bace, R., & Mell, P. (2020). Intrusion detection systems.
Bertoli, G. D. C., Junior, L. A. P., Saotome, O., & dos Santos, A. L. (2023). Generalizing intrusion detection for heterogeneous networks: A stacked-unsupervised federated learning approach. Computers & Security, 127, 103106. https://doi.org/[CrossRef].
Colakovic, A., & Hadzialic, M. (2018). Internet of Things (IoT): A review of enabling technologies, challenges, and open research issues. Computer Networks. https://doi.org/10.1016/j.comnet.2018.07.017.
Cristiano, A. de Souza, Westphall, C. B., Machado, R. B., Sobral, J. B. M., & Vieira, G. dos S. (2020). Hybrid approach to intrusion detection in fog-based IoT environments. Computer Networks, 180, Article 107417. https://doi.org/10.1016/j.comnet.2020.107417.
Darktrace. (n.d.). Available online: https://darktrace.com/ (accessed on March 3, 2022).
Ferrag, M. A., Maglaras, L., Moschoyiannis, S., & Janicke, H. (2020). Deep learning for cyber security intrusion detection: Approaches, datasets, and comparative study. Journal of Information Security and Applications, 50, 102419. https://doi.org/10.1016/j.jisa.2020.102419.
Khraisat, A., & Alazab, A. (2021). A critical review of intrusion detection systems in the Internet of Things: Techniques, deployment strategy, validation strategy, attacks, public datasets, and challenges. Cyber Security, 4(18). https://doi.org/10.1186/s42400-021-00077-7
Mahadik, S., Pawar, P. M., & Muthalagu, R. (2022). Efficient intelligent intrusion detection system for heterogeneous Internet of Things (HetIoT). Journal of Network and Systems Management, 31(2). https://doi.org/10.1007/s10922-022-09620-4
Masdari, M., & Khezri, H. (2020). A survey and taxonomy of the fuzzy signature-based intrusion detection systems. Applied Soft Computing, 92, 106301. https://doi.org/10.1016/j.asoc.2020.106301
Oseni, A., Moustafa, N., Creech, G., Sohrabi, N., Strelzoff, A., Tari, Z., & Linkov, I. (2023). An explainable deep learning framework for resilient intrusion detection in IoT-enabled transportation networks. IEEE Transactions on Intelligent Transportation Systems, 24, 1000–1014. https://doi.org/10.1109/TITS.2022.3179132
Otounm, Y., Liu, D., & Nayak, A. (2019). DL-IDS: A deep learning-based intrusion detection framework for securing IoT. Transactions on Emerging Telecommunications Technologies, Article No. e3803, 1-14. https://doi.org/10.1002/ett.3803
Riyaz, B., & Ganapathy, S. (2020). A deep learning approach for effective intrusion detection in wireless networks using CNN. Soft Computing, 24, 17265–17278.
Satam, P., & Hariri, S. (2021). WIDS: An anomaly-based intrusion detection system for Wi-Fi (IEEE 802.11) protocol. IEEE Transactions on Network and Service Management, 18, 1077–1091.
Tahsien, S., Karimipour, H., & Spachos, P. (2020). Machine learning-based solutions for Internet of Things (IoT) security: A survey. Journal of Network and Computer Applications, 161, 102630. https://doi.org/10.1016/j.jnca.2020.102
