ANALYSIS OF OPPORTUNITIES TO IMPROVE THE SECURITY OF CLOUD INFRASTRUCTURE USING NLP AND ML

DOI: 10.31673/2409-7292.2025.026884

Abstract

As data volumes and the complexity of multi-cloud environments grow, ensuring cybersecurity of cloud infrastructure
is becoming an increasingly difficult task. Traditional approaches based on static rules, signature analysis and centralized SIEM
systems show limited effectiveness when working with dynamic resources and adaptive attacks, such as ART campaigns, insider
threats or zero-day exploits. This necessitates the implementation of intelligent analysis and response mechanisms that can
quickly correlate heterogeneous events and reduce the number of false positives. The integration of natural language processing
(NLP) and machine learning (ML) technologies opens up new opportunities for automating incident analytics, semantic parsing
of event logs (hereinafter referred to as logs) and classifying threats by risk level. NLP modules allow processing large arrays
of unstructured text data — event logs, user messages and configuration files — and identifying sociotechnical attack patterns.
ML algorithms, in turn, provide anomaly detection using classification, clustering, and behavioral analytics (UEBA), which
allows you to predict potential attacks before they are implemented. Modern cybersecurity concepts, in particular the Zero Trust
model and the Principle of Least Privilege (PoLP), combined with the Security as Code approach, create the basis for dynamic
access control and automated rights management. Architectural solutions combining Cloud IAM, PAM, and CIEM are
complemented by AI-driven mechanisms for real-time query context assessment and automated verification of excessive
privileges. This helps reduce response time and increase the adaptability of security policies. This study systematically reviewed
more than ten modern scientific publications covering practical implementations of intelligent DLP systems, automated threat
detection mechanisms in AWS, Azure, and GCP, as well as approaches to integrating NLP/ML into CI/CD processes and SOAR
platforms. Requirements for building adaptive, context-sensitive solutions are formulated, taking into account scalability,
interpretable artificial intelligence (Explainable AI) and compliance with ethical and legal norms (GDPR, ISO/IEC 27001). The
results of the study prove that a combined approach based on NLP and ML allows to significantly reduce the number of false
positives, reduce the average response time to incidents and increase the accuracy of detecting complex threats. The obtained
conclusions will be useful for IT departments, security engineers and DevOps teams seeking to optimize cyber protection
processes in dynamic multi-cloud environments.
Keywords: cybersecurity, cloud technologies, NLP, ML, Zero Trust, Security as Code, UEBA, DLP.

References
1. K.C. Sunkara, K. Narukulla, AI Enhanced Ontology Driven NLP for Intelligent Cloud Resource Query
Processing Using Knowledge Graphs, Independent Research Report, IEEE Senior Members, Raleigh/San Jose, USA
(2023). doi: 10.48550/arXiv.2502.18484.
2. Rajendra Muppalaneni, Anil Chowdary Inaganti and Nischal Ravichandran, AI-Enhanced Data Loss
Prevention (DLP) Strategies for Multi-Cloud Environments, Journal of Computing Innovations and Applications, 2(2),
pp. 1–13. (2024). Available at: https://ciajournal.com/index.php/jcia/article/view/9 (Accessed: 10 May 2025).
3. Jaya J. Application of Deep Learning in Cloud Security. Deep Learning Approaches to Cloud Security.
(2022). doi: 10.1002/9781119760542.ch12
4. J.S. Nimbhorkar, AI Enabled Cloud RAN Test Automation: Automatic Test Case Prediction Using Natural
Language Processing and Machine Learning Techniques, M.Sc. Thesis, KTH Royal Institute of Technology, Ericsson
AB, Stockholm (2023). URN: urn:nbn:se:kth:diva-340090
5. T.K. Vashishth, V. Sharma, B. Kumar, S. Chaudhary, R. Panwar, Enhancing Cloud Security: The Role of
Artificial Intelligence and Machine Learning, In: IGI Global, Chapter 4 (2024). doi: 10.4018/979-8-3693-1431-9.ch004.
6. R.K. Jha, Strengthening Smart Grid Cybersecurity: An In-Depth Investigation into the Fusion of Machine
Learning and Natural Language Processing, J. Trends Comput. Sci. Smart Technol. 5(3) (2023) 284–301. doi:
10.36548/jtcsst.2023.3.005.
7. Y.I. Alzoubi, A. Mishra, A.E. Topcu, Research trends in deep learning and machine learning for cloud
computing security, Artif. Intell. Rev. 57 (2024) 132. doi: 10.1007/s10462-024-10776-5.
8. Martseniuk, Y., Partyka, A., Harasymchuk, O., Nyemkova, E., Karpinski, M. Shadow IT risk analysis in
public cloud infrastructure (2024) CEUR Workshop Proceedings, 3800, pp. 22-31. URN: urn:nbn:de:0074-3800-2.
9. Martseniuk, Y., Partyka, A., Harasymchuk, O., Shevchenko, S. Universal centralized secret data management
for automated public cloud provisioning (2024) CEUR Workshop Proceedings, 3826, pp. 72-81. URN: urn:nbn:de:0074-
3826-1.
10. Volodymyr Khoma, Aziz Abibulaiev, Andrian Piskozub, and Taras Kret. Comprehensive Approach for
Developing an Enterprise Cloud Infrastructure (2024) CEUR Workshop Proceedings, 3654, pp. 201-215. URN:
urn:nbn:de:0074-3654-7.
11. S.R. Mamidi, The Role of AI and Machine Learning in Enhancing Cloud Security, J. Artif. Intell. Gen. Sci.
3(1) (2024). doi: 10.5281/zenodo.10987665.
12. J. Wang, AI/ML-Powered Cybersecurity and Cloud Computing Strategies for Optimized Business
Intelligence in ERP Cloud, ResearchGate (2023). doi: 10.13140/RG.2.2.27926.66882.
13. K. Rangappa, A.K.B. Ramaswamy, M. Prasad, S.A. Kumar, A Secure Cloud Service for Managing User’s
Crucial Data Using NLP, Blockchain, and Smart Contracts, Preprints.org (2024). doi: 10.20944/preprints202409.1738.v1.
14. Buttar AM, Shahzad F, Jamil U. Conversational AI: Security Features, Applications, and Future Scope at
Cloud Platform. Conversational Artificial Intelligence, (2024). doi: 10.1002/9781394200801.ch3.
15. T.-M. Georgescu, Natural Language Processing Model for Automatic Analysis of Cybersecurity-Related
Documents, Symmetry 12(3) (2020) 354. doi: 10.3390/sym12030354.
16. Belal MM, Sundaram DM. Comprehensive review on intelligent security defences in cloud: Taxonomy,
security issues, ML/DL techniques, challenges and future trends. Journal of King Saud University-Computer and
Information Sciences. (2022). doi: 10.1016/j.jksuci.2022.08.035.
17. J. Wang, AI/ML-Powered Cybersecurity and Cloud Computing Strategies for Optimized Business
Intelligence in ERP Cloud, ResearchGate (2023). doi: 10.13140/RG.2.2.27926.66882.
18. Nina P, Ethan K. AI-driven threat detection: Enhancing cloud security with cutting-edge technologies.
International Journal of Trend in Scientific Research and Development, Volume-4, pp.1362-1374. (2019). Available at:
https://www.ijtsrd.com/papers/ijtsrd29520.pdf (Accessed 12 May 2025).
19. Z. Kilhoffer and M. Bashir, Cloud Privacy Beyond Legal Compliance: An NLP Analysis of Certifiable
Privacy and Security Standards, IEEE Cloud Summit, Washington, DC, USA, pp. 79-86, (2024). doi: 10.1109/CloudSummit61220.2024.00020.
20. Sunkara KC, Narukulla K. AI Enhanced Ontology Driven NLP for Intelligent Cloud Resource Query
Processing Using Knowledge Graphs, (2025). doi: 10.48550/arXiv.2502.18484.
21. Mamidi SR. The Role of AI and Machine Learning in Enhancing Cloud Security. Journal of Artificial
Intelligence General science (JAIGS), (2024). doi: 10.60087/jaigs.v3i1.161.
22. D. M. Rakgoale, H. I. Kobo, Z. Z. Mapundu and T. N. Khosa, A Review of AI/ML Algorithms for Security
Enhancement in Cloud Computing with Emphasis on Artificial Neural Networks, 4th International Multidisciplinary
Information Technology and Engineering Conference (IMITEC), Vanderbijlpark, South Africa, pp. 329-336, (2024). doi:
10.1109/IMITEC60221.2024.10851076.
23. Talati, N. D. V., Scalable AI and data processing strategies for hybrid cloud environments, World Journal of
Advanced Research and Reviews, 10(3), pp. 482–492, (2021), doi: 10.30574/wjarr.2021.10.3.0289.
24. Al Saidat MR, Yerima SY, Shaalan K. Advancements of SMS Spam Detection: A Comprehensive Survey
of NLP and ML Techniques. Procedia Computer Science, (2024). doi: 10.1016/j.procs.2024.10.198.
25. H. Aldawsari, S.A. Kouchay, Integrating AI and Machine Learning Algorithms in Cloud Security
Frameworks for Enhanced Proactive Threat Detection and Mitigation, J. Eng. Technol. Manag. 74 (2024). Available at:
https://ciajournal.com/index.php/jcia/article/view/9 (Accessed: 11 May 2025).
26. Mohamed, N., Current trends in AI and ML for cybersecurity: A state-of-the-art survey. Cogent
Engineering, 10(2), (2023). doi: 10.1080/23311916.2023.2272358.