Е-Публикации
Технически университет - София

Abstract: Nowadays the use of Artificial Intelligence (AI) around the globe is constantly growing. These processes were accelerated even more due to the COVID-19 pandemic. In the cybersecurity realm, the real implementations of AI solutions are also constantly growing. For some enterprises, AI is considered more as a risk for overall cybersecurity while others see AI as the way forward to achieve cyber resilience. That kind of uncertainty points out that cybersecurity leaders are still not united around AI and do not fully understand the effects of utilizing it. That lack of understanding is emphasizing again the need for more research into AI for cybersecurity and in addition to that the urgency of attracting young talent to the cybersecurity career path. On the other hand, cyber threat actors are getting more and more sophisticated and may already be on the way to integrating AI into their future attacks. In this paper, we are analyzing the artificial intelligence methods for cybersecurity in Industry 4.0. In addition, we detail the challenges, motivations, and pre-conditions to be taken into consideration when using these AI methods for improving overall cybersecurity in Industry 4.0.

References

1. E. Sabev, G. Pavlova, R. Trifonov, K. Raynova and G. Tsochev, "Analysis of practical cyberattack scenarios for wind farm SCADA systems," 2021 International Conference Automatics and Informatics (ICAI), 2021, pp. 420-424, DOI: 10.1109/ICAI52893.2021.9639550.
2. Radanliev, P., De Roure, D., Walton, R. et al. Artificial intelligence and machine learning in dynamic cyber risk analytics at the edge. SN Appl. Sci. 2, 1773 (2020). https://doi.org/10.1007/s42452-020-03559-4.
3. CoNSS, Committee on National Security Systems (2010) National information assurance (IA) glossary. Fort George G., Meade, MD, https://rmf.org/wp-content/uploads/2017/10/CNSSI-4009.pdf
4. Poremba, S. (2021) Data Poisoning: When Attackers Turn AI and ML Against You. Available at: https://securityintelligence.com/articles/data-poisoning-ai-and-machine-learning/ (Accessed: 10 October 2021).
5. Harri Ruoslahti, Bríd Davis, "Societal Impacts of Cyber Security Assets of Project ECHO," WSEAS Transactions on Environment and Development, vol. 17, p.1274-1283, 2021.
6. Sahli Nabila, Benmohammed Mohamed, Artificial Intelligence and Cyber Security: Protecting and Maintaining Industry 4.0 Power Networks, http://ceur-ws.org/Vol-2748/IAM2020_paper_35.pdf.
7. Annoni, A., Benczur, P., Bertoldi, P., Delipetrev, B., De Prato, G., Feijoo, C., Fernandez Macias, E., Gomez Gutierrez, E., Iglesias Portela, M., Junklewitz, H., Lopez Cobo, M., Martens, B., Figueiredo Do Nascimento, S., Nativi, S., Polvora, A., Sanchez Martin, J.I., Tolan, S., Tuomi, I. and Vesnic Alujevic, L., Artificial Intelligence: A European Perspective, Craglia, M. editor(s), EUR 29425 EN, Publications Office of the European Union, Luxembourg, 2018, ISBN:978-92-79-97217-1, DOI: 10.2760/11251, JRC113826.
8. CEPS Task Force Report (2021) Artificial Intelligence and Cybersecurity, Technology, Governance and Policy Challenges. Available at: https://www.ceps.eu/wp-content/uploads/2021/05/CEPS-TFR-ArtificialIntelligence-and-Cybersecurity.pdf (Accessed: 15 December 2021)
9. European Union Agency for Cybersecurity (ENISA) (2021) Securing Machine Learning Algorithms. Available at: https://www.enisa.europa.eu/publications/securing-machine-learning-algorithms (Accessed: 20 January 2022)
10. Barrett, Matt., Marron, Jeff., Yan Pillitteri, Victoria., Boyens, Jon., Witte, Greg., and Feldman, Larry, “Draft NISTIR 8170, The Cybersecurity Framework: Implementation Guidance for Federal Agencies,” Maryland, 2017.
11. NIST (2018) Cybersecurity Framework Version 1.1. Available at: https://www.nist.gov/newsevents/news/2018/04/nist-releases-version-11-its-popular-cybersecurity-framework (Accessed: 17 June 2018).
12. NIST (2021) NIST Requests Information to Help Develop an AI Risk Management Framework. Available at: https://www.nist.gov/news-events/news/2021/07/nist-requests-information-help-develop-ai-risk-managementframework (Accessed: 1 August 2021).
13. IBM (2021) Supervised learning. Available at: https://www.ibm.com/cloud/learn/supervised-learning#tocwhat-is-su-d3nKa9tk (Accessed: 10 April 2023).
14. IBM (2021) Unsupervised learning. Available at: https://www.ibm.com/cloud/learn/supervised-learning#tocunsupervis-Fo3jDcmY (Accessed: 10 April 2023).
15. IBM (2021) Semi-supervised learning. Available at: https://www.ibm.com/cloud/learn/supervisedlearning#toc-unsupervis-Fo3jDcmY (Accessed: 10 April 2023).
16. IBM (2021) What are recurrent neural networks. Available at: https://www.ibm.com/cloud/learn/recurrentneural-networks (Accessed: 10 April 2023)
17. ScienceDirect (2023) Deep Belief Network. Available https://www.sciencedirect.com/topics/engineering/deep-belief-network (Accessed 20 April 2023).
18. ScienceDirect (2023) Deep Boltzmann Machine. Available at: https://www.sciencedirect.com/topics/engineering/deep-boltzmann-machine (Accessed: 20 April 2023).
19. Derlat, A. (2017) Applied Deep Learning - Part 3: Autoencoders. Available at: https://towardsdatascience.com/applied-deep-learning-part-3-autoencoders-1c083af4d798 (Accessed: 10 February 2023).
20. Brownlee, J. (2019) A Gentle Introduction to Generative Adversarial Networks (GANs). Available at: https://machinelearningmastery.com/what-are-generative-adversarial-networks-gans/ (Accessed: 15 March 2023).
21. Communication-Efficient Learning of Deep Networks from Decentralized Data, https://arxiv.org/pdf/1602.05629.pdf.
22. D. L. Marino, C. S. Wickramasinghe, V. K. Singh, J. Gentle, C. Rieger and M. Manic, "The Virtualized Cyber-Physical Testbed for Machine Learning Anomaly Detection: A Wind Powered Grid Case Study," in IEEE Access, vol. 9, pp. 159475-159494, 2021, DOI: 10.1109/ACCESS.2021.3127169.
23. Graf, P. (2019) Innovative Optimization and Control Methods for Highly Distributed Autonomous Systems. Available at: https://www.nrel.gov/docs/fy19osti/74798.pdf (Accessed: 20 February 2023).
24. Nassim Laouti, Nida Sheibat-Othman, Sami Othman, Support Vector Machines for Fault Detection in Wind Turbines, IFAC Proceedings Volumes, Volume 44, Issue 1, 2011, p. 7067-7072, https://doi.org/10.3182/20110828-6-IT-1002.02560.
25. Farhad Elyasichamazkoti, Abolhasan Khajehpoor, Application of machine learning for wind energy from design to energy-Water nexus: A Survey, Energy Nexus, Volume 2, 2021, p. 100011, https://doi.org/10.1016/j.nexus.2021.100011.
26. Xiao, C.; Liu, Z.; Zhang, T.; Zhang, X. Deep Learning Method for Fault Detection of Wind Turbine Converter. Appl. Sci. 2021, 11, 1280. https://doi.org/10.3390/app11031280.
27. Rashid, H.; Batunlu, C. Anomaly Detection of Wind Turbine Gearbox based on SCADA Temperature Data using Machine Learning. Preprints 2021, 2021010356, DOI: 10.20944/preprints202101.0356.v1.
28. Kateryna Kraus, Nataliia Kraus, Mariia Hryhorkiv, Ihor Kuzmuk, Olena Shtepa, "Artificial Intelligence in Established of Industry 4.0," WSEAS Transactions on Business and Economics, vol. 19, p.1884-1900, 2022.
29. W. Bi, G. Chen and K. Zhang, "Profit-Oriented False Data Injection Attack Against Wind Farms and Countermeasures," in IEEE Systems Journal, vol. 16, no. 3, pp. 3700-3710, Sept. 2022, DOI: 10.1109/JSYST.2021.3107910.
30. Amarjit Datta and Mohammad Ashiqur Rahman. 2017. Cyber Threat Analysis Framework for the Wind Energy Based Power System. In Proceedings of the 2017 Workshop on Cyber-Physical Systems Security and PrivaCy (CPS '17). Association for Computing Machinery, New York, USA, p.81–92. https://doi.org/10.1145/3140241.3140247.
31. Greenberg, A. (2017) Researchers Found They Could Hack Entire Wind Farms. Available at: https://www.wired.com/story/wind-turbine-hack/ (Accessed: 30 January 2020).
32. Comiter, M. (2019) Attacking Artificial Intelligence: AI’s Security Vulnerability and What Policymakers Can Do About It. Available at: https://www.belfercenter.org/publication/AttackingAI (Accessed: 10 January 2023).
33. Eugene Bagdasaryan, Andreas Veit, Yiqing Hua, Deborah Estrin, Vitaly Shmatikov Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics, PMLR 108, p.2938-2948, 2020.
34. N. Muller, D. Kowatsch and K. Bottinger, "Data Poisoning Attacks on Regression Learning and Corresponding Defenses," in 2020 IEEE 25th Pacific Rim International Symposium on Dependable Computing (PRDC), Perth, Australia, 2020 p. 80-89.DOI: 10.1109/PRDC50213.2020.00019.
35. Todorova, M. (2022) Research and Evaluation of a “Protective Shell” for two Industrial Cyber Physical System (CPS) Incidents. Available at: https://tu-dresden.de/ing/informatik/smt/st/dieprofessur/mitarbeiter/?person=4&embedding_id=1e8badf421c649b89f65fb84a05ecbb0&set_language=de (Accessed: 20 September 2022)
36. DARPA GARD program (2021) Holistic Evaluation of Adversarial Defenses. Available at: https://www.gardproject.org/#gard (Accessed: 20 March 2023)

Issue