Trends and challenges: artificial intelligence methods in cybersecurity

This article analyzes the current state of artificial intelligence in cybersecurity. It discusses the principle of integrating artificial intelligence into the security environment based on the "human-in-the-loop" concept. It is noted that the development of software multi-agent systems enables the creation of distributed information security ecosystems. Deep learning methods are analyzed, which form the technological foundation of modern artificial intelligence in cybersecurity due to their ability to automatically extract hierarchical features from raw data. It is shown that hybrid architectures combining the strengths of various neural network paradigms are actively used to improve efficiency, reliability, and interpretability. Artificial intelligence also serves as an active component in operational resilience management, that is, the ability of an organization to perform its key functions in the face of cyberattacks or the failure of certain infrastructure subsystems. Key trends and challenges in the development of artificial intelligence in cybersecurity are identified. Promising areas of development include explainable artificial intelligence, federated learning, large-scale language models, and protection against adversarial artificial intelligence. Key implementation challenges include real-time scalability, attack evolution, and operational complexity.

1. Olawade D.B., Plabon Sh.B., Ojo A., Ogunbona M.A., Makanjuola B.D., Olasilola O.R. Human in the loop artificial intelligence in healthcare: applications, outcomes, and implementation challenges. International Journal of Medical Informatics. 2026;213:106362. https://doi.org/10.1016/j.ijmedinf.2026.106362

2. Alqudhaibi A., Albarrak M., Aloseel A., et al. Proactive cybersecurity in industry 4.0: a survey of cybersecurity threat prediction approaches in manufacturing systems. International Journal of Information Security. 2026;25(1):14. https://doi.org/10.1007/s10207-025-01188-9

3. Valeev S.S., Kondratyeva N.V., Melnikov A.V. Enterprise architecture and zero trust architecture. Journal of the Ural Federal District. Information security. 2023;2(2):49–53. (In Russ.). https://doi.org/10.14529/secur230204

4. Duran F., Conrad S.H., Conrad G.N., Duggan D.P., Held E.B. Building a system for insider security. IEEE Security & Privacy. 2009;7(6):30–38. https://doi.org/10.1109/MSP.2009.111

5. Alladi T., Chamola V., Zeadally Sh. Industrial control systems: Cyberattack trends and countermeasures. Computer Communications. 2020;155(22):1–9. https://doi.org/10.1016/j.comcom.2020.03.007

6. Valeev S.S., Kondratyeva N.V., Guzairov M.B., Melnikov A.V. Stages of reengineering the information system of the enterprise within the framework of zero trust technology. Vestnik of the Russian New University. Series: Complex Systems: models, analysis and management. 2023;(3):136–143. (In Russ.).

7. Valeev S.S., Kondratyeva N.V., Guzairov M.B., Ismagilova A.S. Hierarchical Dynamic Information Security Management System for an Enterprise Information System. Engineering Journal of Don. 2023;(11). (In Russ.). URL: https://ivdon.ru/en/magazine/archive/n11y2023/8802

8. Valeev S.S., Kondratyeva N.V., Guzairov M.B., Ismagilova A.S. Multi-agent systems as a technological basis for the implementation of zero trust concept. Vestnik of the Russian New University. Series: Complex Systems: models, analysis and management. 2024;(3):116–123. (In Russ.).

9. Page M.J., McKenzie J.E., Bossuyt P.M., et al. The PRISMA 2020 statement: an updated guideline for reporting systematic reviews. The BMJ. 2021;372:n71. https://doi.org/10.1136/bmj.n71

10. Heckman K.E., Stech F.J., Thomas R.K., Schmoker B., Tsow A.W. Intrusions, Deception, and Campaigns. In: Cyber Denial, Deception and Counter Deception: A Framework for Supporting Active Cyber Defense. Cham: Springer; 2015. P. 31–52. https://doi.org/10.1007/978-3-319-25133-2_3

11. Ding D., Han Q.-L., Xiang Y., Ge X., Zhang X.-M. A survey on security control and attack detection for industrial cyber-physical systems. Neurocomputing. 2018;275:1674–1683. https://doi.org/10.1016/j.neucom.2017.10.009

12. Valeev S.S., Kondratyeva N.V. Features of designing security systems based on zero trust architecture. Engineering Journal of Don. 2023;(8). (In Russ.). URL: https://ivdon.ru/en/magazine/archive/n8y2023/8627

13. Yan J., Qi Y., Rao Q. Detecting malware with an ensemble method based on deep neural network. Security and Communication Networks. 2018;2018:7247095. https://doi.org/10.1155/2018/7247095

14. Venkatraman S., Alazab M., Ravi V. A hybrid deep learning image-based analysis for effective malware detection. Journal of Information Security and Applications. 2019;47:377–389. https://doi.org/10.1016/j.jisa.2019.06.006

15. Zhang J., Qin Zh., Yin H., Ou L., Xiao Sh., Hu Y. Malware variant detection using opcode image recognition with small training sets. In: 2016 25th International Conference on Computer Communication and Networks (ICCCN), 01–04 August 2016, Waikoloa, HI, USA. IEEE; 2016. https://doi.org/10.1109/ICCCN.2016.7568542

16. Zhou G., Tian W., Buyya R., Xue R., Song L. Deep reinforcement learning-based methods for resource scheduling in cloud computing: a review and future directions. Artificial Intelligence Review. 2024;57(5):124. https://doi.org/10.1007/s10462-024-10756-9

17. Zohrevand Z., Glässer U. Should I raise the red flag? A comprehensive survey of anomaly scoring methods toward mitigating false alarms. arXiv. URL: https://arxiv.org/abs/1904.06646 [Accessed 5th June 2026].

18. Park J., Kim D.S., Lim H. Privacy-preserving reinforcement learning using homomorphic encryption in cloud computing infrastructures. IEEE Access. 2020;8:203564–203579. https://doi.org/10.1109/ACCESS.2020.3036899

19. Thakur P., Kansal V., Rishiwal V. Hybrid deep learning approach based on LSTM and CNN for malware detection. Wireless Personal Communications. 2024;136(3):1879–1901. https://doi.org/10.1007/s11277-024-11366-y

20. Akandwanaho S.M., Kooblal M. Intelligent Malware Detection Using a Neural Network Ensemble Based on a Hybrid Search Mechanism. The African Journal of Information and Communication. 2019;(24). https://doi.org/10.23962/10539/28660

21. Yakura H., Shinozaki Sh., Nishimura R., Oyama Y., Sakuma J. Malware analysis of imaged binary samples by convolutional neural network with attention mechanism. In: CODASPY '18: Proceedings of the Eighth ACM Conference on Data and Application Security and Privacy, 19–21 March 2018, Tempe, AZ, USA. New York: ACM; 2018. P. 127–134. https://doi.org/10.1145/3176258.3176335

22. Yoo S., Kim S., Kang B.B. The image game: exploit kit detection based on recursive convolutional neural networks. IEEE Access. 2020;8:18808–18821. https://doi.org/10.1109/ACCESS.2020.2967746

23. Yazı A.F., Çatak F.Ö., Gül E. Classification of methamorphic malware with deep learning (LSTM). In: 2019 27th Signal Processing and Communications Applications Conference (SIU), 24–26 April 2019, Sivas, Turkey. IEEE; 2019. https://doi.org/10.1109/SIU.2019.8806571

24. Yue S., Wang T. Imbalanced malware images classification: a CNN based approach. arXiv. URL: https://arxiv.org/abs/1708.08042 [Accessed 5th June 2026].

25. Wang T., Xu N. Malware variants detection based on opcode image recognition in small training set. In: Proceedings of the 2017 IEEE 2nd International Conference on Cloud Computing and Big Data Analysis (ICCCBDA), 28–30 April 2017, Chengdu, China. IEEE; 2017. P. 328–332. https://doi.org/10.1109/ICCCBDA.2017.7951933

26. Khan R., Maynard P., McLaughlin K., Laverty D., Sezer S. Threat analysis of BlackEnergy malware for synchrophasor based real-time control and monitoring in smart grid. In: ICS-CSR '16: Proceedings of the 4th International Symposium for ICS & SCADA Cyber Security Research 2016, 23–25 August 2016, Belfast, UK. Swindon: BCS Learning & Development Ltd.; 2016. https://doi.org/10.14236/ewic/ICS2016.7

27. Crossman A., Plummer A.R., Sekharudu Ch., Warrier D., Yekrangian M. Auspex: Building threat modeling tradecraft into an artificial intelligence-based copilot. In: 2025 IEEE Conference on Artificial Intelligence (CAI), 05–07 May 2025, Santa Clara, CA, USA. IEEE; 2025. P. 1160–1167. https://doi.org/10.1109/CAI64502.2025.00201

28. Bhardwaj A., Godika S., Loonker Y. MALCDF: A Distributed Multi-Agent LLM Framework for Real-Time Cyber. arXiv. URL: https://arxiv.org/abs/2512.14846 [Accessed 8th June 2026].

29. Georgiadou A., Mouzakitis S., Askounis D. Assessing MITRE ATT&CK Risk Using a Cyber-Security Culture Framework. Sensors. 2021;21(9):3267. https://doi.org/10.3390/s21093267

30. Friedberg I., Skopik F., Settanni G., Fiedler R. Combating advanced persistent threats: From network event correlation to incident detection. Computers & Security. 2014;48:35–57. https://doi.org/10.1016/j.cose.2014.09.006

31. Hundman K., Constantinou V., Laporte Ch., Colwell I., Soderstrom T. Detecting spacecraft anomalies using LSTMs and nonparametric dynamic thresholding. arXiv. URL: https://arxiv.org/abs/1802.04431 [Accessed 8th June 2026].

32. Laheri R., Sukumar H.K.K., Kola Ch., Makin Y. Self-healing infrastructure: leveraging reinforcement learning for autonomous cloud recovery and enhanced resilience. Journal of Information Systems Engineering and Management. 2025;10(49s):352–357. https://doi.org/10.52783/jisem.v10i49s.9888

33. Mehdi Syed A.A., Anazagasty E. AI-driven infrastructure automation: leveraging AI and ML for self-healing and auto-scaling cloud environments. International Journal of Artificial Intelligence, Data Science, and Machine Learning. 2024;5(1):32–43. https://doi.org/10.63282/3050-9262.IJAIDSML-V5I1P104

34. Thein Th., Myo M.M., Parvin S., Gawanmeh A. Reinforcement learning based methodology for energy-efficient resource allocation in cloud data centers. Journal of King Saud University – Computer and Information Sciences. 2020;32(10):1127–1139. https://doi.org/10.1016/j.jksuci.2018.11.005

35. Mangalampalli S., Karri G.R., Kumar M., et al. DRLBTSA: Deep reinforcement learning based task-scheduling algorithm in cloud computing. Multimedia Tools and Applications. 2024;83(3):8359–8387. https://doi.org/10.1007/s11042-023-16008-2

36. Sharma A., Singh U.K. Modelling of smart risk assessment approach for cloud computing environment using AI and supervised machine learning algorithms. Global Transitions Proceedings. 2022;3(1):243–250. https://doi.org/10.1016/j.gltp.2022.03.030

37. Qu G., Wu H., Li R., Jiao P. DMRO: A deep meta reinforcement learning-based task offloading framework for edge-cloud computing. IEEE Transactions on Network and Service Management. 2021;18(3):3448–3459. https://doi.org/10.1109/TNSM.2021.3087258

38. Sheela M.S., Jayakanth J.J., Ramathilagam A., Gracewell J. Secure wireless sensor network transmission using reinforcement learning and homomorphic encryption. International Journal of Data Science and Analytics. 2025;20(3):2851–2870. https://doi.org/10.1007/s41060-024-00633-7

39. Joshi V., Patel P., Chandwani N., Bhatia J., Kumhar M. Intelligent auto-scaling in cloud infrastructure using machine learning and reinforcement learning. In: Advances in Data-Driven Computing and Intelligent Systems: Selected Papers from ADCIS 2024: Volume 2, 20–21 September 2024, Goa, India. Singapore: Springer; 2024. P. 217–239. https://doi.org/10.1007/978-981-96-4536-7_17

40. Jha N.N. Accelerating Cloud Outage Recovery Through Adaptive AI: A Reinforcement Learning Approach. European Journal of Computer Science and Information Technology. 2025;13(20):1–10. https://doi.org/10.37745/ejcsit.2013/vol13n26110