Joint application of artificial immune system mechanisms in the integrated system for detecting attacks on Industrial Internet of Things

The article considers the issue of detecting network attacks on the Industrial Internet of Things (IIoT) systems. The widespread use of such systems causes an increase in the vulnerability of corporate networks due to the low security of smart devices, the distributed architecture of IIoT networks, and the heterogeneous nature of IIoT devices. The article proposes to employ an advanced artificial immune system aimed at intrusion detection in the IIoT network. The main concepts and mechanisms of artificial immunity currently utilized to solve various kinds of information security and data mining problems are analyzed. Such algorithms as algorithms of negative selection, clonal selection, automatic updating of detectors, danger theory, dendritic cells and idiopathic immune network theory are examined. The features of each approach are regarded; the advantages of their joint application in integrated intrusion detection system are demonstrated. For the purposes of training and evaluating the efficiency of the given system, a set of testing data on the network interaction of Internet of things devices (Bot-IoT) was used. The results of the computational experiments verify the high efficiency of the suggested approach.

1. Into the mind of an IoT hacker | how to protect IoT networks & devices. RSA Conference. 2021. Available by: https://www.rsaconference.com/Library/presentation/USA/2021/Into%20the%20Mind%20of%20an%20IoT%20Hacker%20%20How%20to%20Protect%20IoT%20Networks%20%20Devices (accessed on 10.09.2022).

2. Zashchishchat' IoT v seti ili zashchishchat' set' ot IoT. Laboratoriya Kasperskogo = Kaspersky Lab. Available by: https://www.kaspersky.ru/blog/rsa2021-dangerous-iot/30870/ (accessed on 10.09.2022) (In Russ.).

3. Industrial Internet of Things – IIoT. Промышленный интернет вещей. TADVISER. Available by: https://www.tadviser.ru/index.php/%D0%A1%D1%82%D0%B0%D1%82%D1%8C%D1%8F:IIoT_-_Industrial_Internet_of_Things_(%D0%9F%D1%80%D0%BE%D0%BC%D1%8B%D1%88%D0%BB%D0%B5%D0%BD%D0%BD%D1%8B%D0%B9_%D0%B8%D0%BD%D1%82%D0%B5%D1%80%D0%BD%D0%B5%D1%82_%D0%B2%D0%B5%D1%89%D0%B5%D0%B9) (accessed on 10.09.2022).

4. Protic D.D. Intrusion detection based on the artificial immune system. Vojnoteh. glas. 2020;4. Available by: https://cyberleninka.ru/article/n/intrusion-detection-based-on-the-artificial-immune-system (accessed on 23.09.2022).

5. Chastikova V.A., Kartamyshev D.A. Artificial immune system: basic approaches and feature of their realization. Nauchnye trudy KubGTU = Scientific Works of the Kuban State Technological University. 2016;8:193–208. (In Russ.).

6. Brown J., Anwar M., Dozier G. An artificial immunity approach to malware detection in a mobile platform. URASIP Journal on Information Security. 2017:7. Available by: https://jis-eurasipjournals.springeropen.com/articles/10.1186/s13635-017-0059-2 (accessed on 20.09.2022).

7. Kumaravel H.V. An anomaly-based intrusion detection system based on artificial immune system (AIS) techniques. Open Access Theses. 2016:964. Available by: https://docs.lib.purdue.edu/open_access_theses/964 (accessed on 25.08.2022).

8. Burlakov M.E., Ivkin A.N. Intrusion detection system based on the artificial immune system. Vestnik PNIPU = PNRPU Bulletin. 2019;29:209–224. (In Russ.).

9. Limon-Cantu D., Alarcon-Aquino V. Network intrusion detection using dendritic cells and danger theory. Technology, Science and Culture: A Global Vision. 2020;23:89–106.

10. The UNSW-NB15 Dataset, University of New South Wales. Available by: https://research.unsw.edu.au/projects/unsw-nb15-dataset (accessed on 25.09.2022).

11. NSL-KDD. University of New Brunswick. Available by: https://www.unb.ca/cic/datasets/nsl.html. (accessed on 25.09.2022).

12. Farzadnia E., Shirazia H., Nowroozi A. A New Intrusion Detection System using the Improved DendriticCell Algorithm. The Computer Journal. 2021;8(64):1193–1214.

13. Duru C., Ladeji-Osias J., Wandji K., Otily T., Kone R. A review of human immune inspired algorithms for intrusion detection systems. 2022 IEEE World AI IoT Congress (AIIoT). 2022:364–371.

14. Selemenev A.V., Astakhova I.F. Application of artificial immune systems for detection of network inclusions. Vestnik VGU = Proceedings of Voronezh State University. 2019;2:49–56. (In Russ.).

15. Alaparthy V., Morgera S. A multi level intrusion detection system for wirel ess sensor networks based on immune theory. IEEE Access. 2018;6:47364–47373.

16. Aldhaheri S., Alghazzawi D., Cheng L., Alzahrani B., Al Barakat A. DeepDCA: Novel network based detection of IoT attacks using artificial immune syste. Applied sciences. 2020;10:1909–1932.

17. The Bot-IoT Dataset, University of New South Wales. Available by: https://research.unsw.edu.au/projects/bot-iot-dataset (accessed on 25.09.2022).

18. Xiao X., Zhang R. A danger theory inspired protection approach for hierarchical wireless sensor networks. KSII Transactions on Internet and Information Systems. 2019;5(13):2732–2753.

19. Vasilyev V.I., Gvozdev V.E., Shamsutdinov R.R. Network Anomaly Detection Based on Artificial Immune System for Industrial Internet of Things. Doklady TUSUR = Proceedings of TUSUR University. 2021;4(21):40–45. (In Russ.).

20. Almomani I., Al-Kasasbeh B., AL-Akhras M. WSN-DS: A Dataset for Intrusion Detection Systems in Wireless Sensor Networks. Journal of Sensors. 2016. Available by: https://www.hindawi.com/journals/js/2016/4731953/ (accessed on 25.09.2022).

21. Vasilyev V.I., Shamsutdinov R.R. Intelligent network intrusion detection system based on artificial immune system mechanisms. Modelirovanie, optimizatsiya i informatsionnye tekhnologii. = Modeling, Optimization and Information Technology. 2019;1(7):521–535. (In Russ.).

22. Vasilyev V.I., Vulfin A.M., Gvozdev V.E., Shamsutdinov R.R. Hybrid intelligent intrusion detection system based on combining machine learning methods. Modelirovanie, optimizatsiya i informatsionnye tekhnologii. = Modeling, Optimization and Information Technology. 2021;9(3). Available by: https://moitvivt.ru/ru/journal/pdf?id=1032 (accessed on 25.09.2022). DOI: 10.26102/2310-6018/2021.34.3.019. (In Russ.).