DETECT ANOMALIES AND STRENGTHEN CYBERSECURITY IN IOT NETWORKS USING HIGH-LEVEL DEEP LEARNING TECHNIQUES

Khalid Murad Abdullah

Authors

Khalid Murad Abdullah Open Educational College, Al-Qadisiyah Center, Iraq

Keywords:

Anomaly detection, Cybersecurity, IoT networks, Deep learning, High-level techniques, Data analysis

Abstract

Specifically, we have worked on applying advanced deep learning techniques to improve cybersecurity in IoT networks and efficiently identify anomalies. First, we collect and prepare the data from the IoT network so that it can be analyzed. This data can be any kind of network traffic, including user interactions, device communication, or sensor readings. Afterwards, we apply deep learning models, It is able to recognize intricate links and patterns in the data. These models are made especially to manage the size and complexity of Internet of Things networks. Depending on the type of data and the particular needs of the anomaly detection task, one popular option is the use of deep neural networks, such as convolutional neural networks (CNNs) or recurrent neural networks (RNNs).A binary cross-entropy loss function is employed in the training phase to steer the learning process and help the model correctly categorize anomalous and typical network events. Furthermore, we take accuracy into account as a performance parameter, which effectively gauges the overall performance of the model in terms of accurate predictions. We use the Receiver Operating Characteristic (ROC) curve and its corresponding metrics, such as the True Positive Rate (TPR) and True Negative Rate (TNR), to assess the efficacy of our methodology. The model's performance across various thresholds is depicted by the ROC curve, which offers insights into the trade-off between true positive and false positive rates. Through the application of these advanced deep learning algorithms and the consideration of metrics such as TPR and TNR, our goal is to improve IoT network security through efficient anomaly detection and mitigation of potential cybersecurity risks.

References

1. Tang, S., Chen, L., He, K., Xia, J., Fan, L., & Nallanathan, A. (2022). Computational intelligence and deep learning for next-generation edge-enabled industrial IoT. IEEE Transactions on Network Science and Engineering. Kolias, C., Stavrou, A., Voas, J., Bojanova, I., & Kuhn, R. (2016). Learning Internet-of-Things security" hands-on". IEEE Security & Privacy, 14(1), 37-46.
2. Kolias, C., Stavrou, A., Voas, J., Bojanova, I., & Kuhn, R. (2016). Learning Internet-of-Things security" hands-on". IEEE Security & Privacy, 14(1), 37-46.
3. Galinina, O., Andreev, S., Balandin, S., & Koucheryavy, Y. (Eds.). (2017). Internet of Things, Smart Spaces, and Next Generation Networks and Systems: 17th International Conference, NEW2AN 2017, 10th Conference, ruSMART 2017, Third Workshop NsCC 2017, St. Petersburg, Russia, August 28–30, 2017, Proceedings (Vol. 10531). Springer.
4. LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. nature, 521(7553), 436-444.
5. Voulodimos, A., Doulamis, N., Doulamis, A., & Protopapadakis, E. (2018). Deep learning for computer vision: A brief review. Computational intelligence and neuroscience, 2018.
6. Chalapathy, R., & Chawla, S. (2019). Deep learning for anomaly detection: A survey. arXiv preprint arXiv:1901.03407.
7. Mohammadi, M., Al-Fuqaha, A., Sorour, S., & Guizani, M. (2018). Deep learning for IoT big data and streaming analytics: A survey. IEEE Communications Surveys & Tutorials, 20(4), 2923-2960.
8. Dina, A. S., Siddique, A. B., & Manivannan, D. (2023). A deep learning approach for intrusion detection in Internet of Things using focal loss function. Internet of Things, 22, 100699.
9. Ullah, I., & Mahmoud, Q. H. (2021). Design and development of a deep learning-based model for anomaly detection in IoT networks. IEEE Access, 9, 103906-103926.
10. Vakili, M., Ghamsari, M., & Rezaei, M. (2020). Performance analysis and comparison of machine and deep learning algorithms for IoT data classification. arXiv preprint arXiv:2001.09636.
11. Woźniak, M., Wieczorek, M., & Siłka, J. (2023). BiLSTM deep neural network model for imbalanced medical data of IoT systems. Future Generation Computer Systems, 141, 489-499.
12. Xie, X., Wu, D., Liu, S., & Li, R. (2017). IoT data analytics using deep learning. arXiv preprint arXiv:1708.03854.
13. Vu, L., Nguyen, Q. U., Nguyen, D. N., Hoang, D. T., & Dutkiewicz, E. (2020). Deep transfer learning for IoT attack detection. IEEE Access, 8, 107335-107344.
14. Ullah, I., & Mahmoud, Q. H. (2021). Design and development of a deep learning-based model for anomaly detection in IoT networks. IEEE Access, 9, 103906-103926.
15. Yavuz, F. Y., Ünal, D., & Gül, E. (2018). Deep learning for detection of routing attacks in the internet of things. Int. J. Comput. Intell. Syst., 12(1), 39-58.
16. Churcher, A., Ullah, R., Ahmad, J., Masood, F., Gogate, M., Alqahtani, F., ... & Buchanan, W. J. (2021). An experimental analysis of attack classification using machine learning in IoT networks. Sensors, 21(2), 446.