Обнаружение аномалий для IIoT: анализ набора данных Edge-IIoTset с различными распределениями классов

Кибербезопасность промышленного интернета вещей (Industrial Internet of Things, IIoT) означает предотвращение несанкционированного доступа, атак и уязвимостей взаимосвязанных устройств, сетей и данных. Учитывая внутреннюю взаимосвязь устройств IIoT, обеспечение безопасности имеет первостепенное значение для предотвращения потенциальных сбоев, утечек данных и вредоносных действий. По мере распространения систем IIoT возрастает важность надежных мер безопасности, эффективного обнаружения вторжений и интеллектуальных методов обнаружения для защиты критически важной инфраструктуры и конфиденциальных данных от киберугроз. В данной работе исследованы вопросы создания безопасной и устойчивой промышленной среды посредством использования гибридной модели: сверточной нейронной сети и глубокой нейронной сети, учитывающей различные распределения классов. Для повышения эффективности модели применен набор данных Edge IIoTset. В процессе оценки использованы различные метрики, включая Accuracy, Precision, Recal и F1-меру. Благодаря тщательной предварительной обработке и использованию различных сценариев распределения классов (2, 6, 9, 10 и 15 классов) модель показала хорошие результаты классификации. Конфигурация с 9 классами достигла точности 99,13 %, в то время как конфигурации с 6 и 10 классами — 97,13 % и 96,11 % соответственно. Предложенная архитектура эффективно сочетает уровни извлечения признаков и глубокой классификации, что приводит к созданию надежного решения, адаптируемого к сложному трафику IIoT.

1. Jaidka H., Sharma N., Singh R. Evolution of IoT to IIoT: applications & challenges. Proc. of the International Conference on Innovative Computing & Communications (ICICC), 2020, pp. 1–6. https://doi.org/10.2139/ssrn.3603739

2. Farhan L., Kharel R., Kaiwartya O., Quiroz-Castellanos M., Alissa A., Abdulsalam M. A concise review on internet of things (IoT)problems, challenges and opportunities. Proc. of the 11th International Symposium on Communication Systems, Networks & Digital Signal Processing (CSNDSP), 2018, pp. 1–6. https://doi.org/10.1109/CSNDSP.2018.8471762

3. Chalishazar T. Peerbits exploring the applications of IoT in different industries, 2023. Available at: https://www.peerbits.com/blog/iotapplications-in-different-industries.html (accessed: 24.06.2023)

4. Qiu T., Chi J., Zhou X., Ning Z., Atiquzzaman M., Wu D.O. Edge computing in Industrial Internet of Things: architecture, advances and challenges. IEEE Communications Surveys & Tutorials, 2020, vol. 22, no. 4, pp. 2462–2488. https://doi.org/10.1109/COMST.2020.3009103

5. Alguliyev R., Imamverdiyev Y., Sukhostat L. Cyber-physical systems and their security issues. Computers in Industry, 2018, vol. 100, no. 1, pp. 212–223.

6. Mohamed N., Al-Jaroodi J., Jawhar I. Cyber–physical systems forensics: today and tomorrow. Journal of Sensor and Actuator Networks, 2020, vol. 9, no. 3, pp. 37. https://doi.org/10.3390/jsan9030037

7. Javaid M., Haleem A., Singh R.P., Suman R., Gonzalez E.S. Understanding the adoption of industry 4.0 technologies in improving environmental sustainability. Sustainable Operations and Computers, 2022, vol. 3, pp. 203–217. https://doi.org/10.1016/j.susoc.2022.01.008

8. Mirani A.A., Velasco-Hernandez G., Awasthi A., Walsh J. Key challenges and emerging technologies in industrial iot architectures: A review. Sensors, 2022, vol. 22, no. 15, pp. 5836. https://doi.org/10.3390/s22155836

9. Younan M., Houssein E.H., Elhoseny M., Ali A.A. Challenges and recommended technologies for the industrial internet of things: A comprehensive review. Measurement, 2020, vol. 151, pp. 107198. https://doi.org/10.1016/j.measurement.2019.107198

10. Gebremichael T., Ledwaba L.P., Eldefrawy M.H., Hancke G.P., Pereira N., Gidlund M., Akerberg J. Security and privacy in the industrial internet of things: current standards and future challenges. IEEE Access, 2020, vol. 8, pp. 152351–152366. https://doi.org/10.1109/ACCESS.2020.3016937

11. Madhuri G.S., Rani M.U. Anomaly detection techniques. Proc. of the IADS International Conference on Computing, Communications & Data Engineering (CCODE), 2018, pp. 1–6.

12. Munir M., Chattha M.A., Dengel A., Ahmed S. A comparative analysis of traditional and deep learning-based anomaly detection methods for streaming data. Proc. of the 18th IEEE International Conference on Machine Learning and Applications (ICMLA), 2019, pp. 561–566. https://doi.org/10.1109/icmla.2019.00105

13. Du J., Yang K., Hu Y., Jiang L. NIDS-CNNLSTM: Network intrusion detection classification model based on deep learning. IEEE Access, 2023, vol. 11, pp. 24808–24821. https://doi.org/10.1109/ACCESS.2023.3254915

14. Kandhro I.A., Alanazi S.M., Ali F., Kehar A., Fatima K., Uddin M. Detection of real-time malicious intrusions and attacks in IoT empowered cybersecurity infrastructures. IEEE Access, 2023, vol. 11, pp. 9136– 9148. https://doi.org/10.1109/ACCESS.2023.3238664

15. Alrowaily M., Alenezi F., Lu Z. Effectiveness of machine learning based intrusion detection systems. Lecture Notes in Computer Science, 2019, vol. 11611, pp. 277–288. https://doi.org/10.1007/978-3-030-24907-6_21

16. Cam N.T., Trung N.G. An intelligent approach to improving the performance of threat detection in IoT. IEEE Access, 2023, vol. 11, pp. 44319–44334. https://doi.org/10.1109/ACCESS.2023.3273160

17. Al-Abassi A., Karimipour H., Dehghantanha A., Pariz R.M. An ensemble deep learning-based cyber-attack detection in industrial control system. IEEE Access, 2020, vol. 8, pp. 83965– 83973. https://doi.org/10.1109/ACCESS.2020.2992249

18. Shone N., Ngoc T.N., Phai V.D., Shi Q. A deep learning approach to network intrusion detection. IEEE Transactions on Emerging Topics in Computational Intelligence, 2018, vol. 2, no. 1, pp. 41–50. https://doi.org/10.1109/TETCI.2017.2772792

19. Ullah I., Mahmoud Q.H. Design and development of a deep learningbased model for anomaly detection in IoT networks. IEEE Access, 2021, vol. 9, pp. 103906–103926. https://doi.org/10.1109/ACCESS.2021.3094024

20. Gümüşbaş D., Yıldırım T., Genovese A., Scotti F. A comprehensive survey of databases and deep learning methods for cybersecurity and intrusion detection systems. IEEE Systems Journal, 2020, vol. 15, no. 2, pp. 1717–1731. https://doi.org/10.1109/JSYST.2020.2992966

21. Ashraf E., Areed N.F., Salem H., Salem H., Abdelhady E., Farouk A. IoT based intrusion detection systems from the perspective of machine and deep learning: a survey and comparative study. Delta University Scientific Journal, 2022, vol. 5, no. 2, pp. 367–386. https://doi.org/10.21608/dusj.2022.275552

22. Thakkar A., Lohiya R. A review of the advancement in intrusion detection datasets. Procedia Computer Science, 2020, vol. 167, pp. 636–645. https://doi.org/10.1016/j.procs.2020.03.330

23. Mishra N., Pandya S. Internet of Things applications, security challenges, attacks, intrusion detection, and future visions: A systematic review. IEEE Access, 2021, vol. 9, pp. 59353–59377. https://doi.org/10.1109/ACCESS.2021.3073408

24. Liu L., Wang P., Lin J., Liu L. Intrusion detection of imbalanced network traffic based on machine learning and deep learning. IEEE Access, 2020, vol. 9, pp. 7550–7563. https://doi.org/10.1109/ACCESS.2020.3048198

25. Ito A., Saito K., Ueno R., Homma N. Imbalanced data problems in deep learning-based side-channel attacks: Analysis and solution. IEEE Transactions on Information Forensics and Security, 2021, vol. 16, pp. 3790–3802. https://doi.org/10.1109/TIFS.2021.3092050

26. Goyal P., Pandey S., Jain K. Deep Learning for Natural Language Processing: Creating Neural Networks with Python. Apress, 2018, 294 p.

27. Chinnathambi R.A., Plathottam S.J., Hossen T., Nair A.S., Ranganathan P. Deep neural networks (DNN) for day-ahead electricity price markets. Proc. of the IEEE electrical power and energy conference (EPEC), 2018, pp. 1–6. https://doi.org/10.1109/EPEC.2018.8598327

28. Rosenblatt F. The perceptron: a probabilistic model for information storage and organization in the brain. Psychological Review, 1958, vol. 65, no. 6, pp. 386–408. https://doi.org/10.1037/h0042519

29. LeCun Y., Boser B., Denker J.S., Henderson D., Howard R.E., Hubbard W., Jackel L.D. Backpropagation applied to handwritten zip code recognition. Neural Computation, 1989, vol. 1, no. 4, pp. 541–551. https://doi.org/10.1162/neco.1989.1.4.541

30. Hubel D.H., Wiesel T.N. Receptive fields and functional architecture of monkey striate cortex. The Journal of Physiology, 1968, vol. 195, no. 1, pp. 215–243. https://doi.org/10.1113/jphysiol.1968.sp008455

31. Yamashita R., Nishio M., Do R.K.G., Togashi K. Convolutional neural networks: an overview and application in radiology. Insights into Imaging, 2018, vol. 9, pp. 611–629. https://doi.org/10.1007/s13244-018-0639-9

32. Ferrag M.A., Friha O., Hamouda D., Maglaras L., Janicke H. EdgeIIoTset: a new comprehensive realistic cyber security dataset of IoT and IIoT applications for centralized and federated learning. IEEE Access, 2022, vol. 10, pp. 40281–40306. https://doi.org/10.1109/access.2022.3165809

33. Khacha A., Saadouni R., Harbi Y., Aliouat Z. Hybrid deep learningbased intrusion detection system for industrial Internet of Things. Proc. of the 5th International Symposium on Informatics and its empowered cybersecurity infrastructures // IEEE Access. 2023. V. 11. P. 9136– 9148. https://doi.org/10.1109/ACCESS.2023.3238664