Journal of Telecommunication, Switching Systems and Networks Review Article
AI-Powered Cloud Storage Security: Intelligent Threat Detection, Adaptive Access Control and Resilient Data Protection
Abstract
Cloud storage has become a basic service for enterprises, educational institutions, digital platforms and electrical/electronic systems that continuously generate data. Its convenience, scalability and remote accessibility also increase exposure to credential theft, ransomware, accidental sharing, malicious insiders, misconfiguration and large-scale data leakage. Conventional security controls such as passwords, static access rules and signature-based detection remain necessary, but they often react after a known pattern has already appeared. This review presents an accessible framework for AI-powered cloud storage security in which artificial intelligence and machine learning support continuous monitoring, anomaly detection, adaptive access control, data loss prevention (DLP) and ransomware response. The proposed architecture combines identity and access management (IAM), zero-trust principles, encryption and key management, immutable backup, cloud telemetry, AI-based risk scoring and security operations. Machine learning is positioned as a decision-support layer rather than a replacement for policy or human oversight. The paper also explains how file-operation patterns, login behavior, device posture, API (Application Programming Interface) activity and data sensitivity labels can be converted into useful security signals. Special attention is given to resilient recovery, explainable alerts, model drift, false positives and governance of AI models. The topic is aligned with electrical and electronics engineering (EEE) through smart-grid, industrial Internet of Things (IoT), embedded-system and edge-device data that are frequently stored or analyzed in the cloud. The resulting framework is suitable for academic demonstration and early institutional planning because it emphasizes clear architecture, practical controls and staged implementation without requiring excessive mathematical depth or proprietary products.
Keywords
References (17)
- Liu F, Tong J, Mao J, Bohn R, Messina J, Badger L, Leaf D. NIST cloud computing reference architecture. NIST special publication. 2011 Sep;500(2011):1-28.
- Rose S, Borchert O, Mitchell S, Connelly S. Zero trust architecture. NIST special publication. 2020 Aug 10;800(207):1-52.
- Force JT. Security and privacy controls for information systems and organizations. National Institute of Standards and Technology; 2020 Mar 16.
- AI N. Artificial intelligence risk management framework (AI RMF 1.0). URL: https://nvlpubs. nist. gov/nistpubs/ai/nist. ai. 2023 Jan;1(0):0-1.
- Abubakar MM, Özen Y. Cloud security frameworks: a comprehensive analysis of security controls, governance models, and implementation challenges in modern cloud infrastructures. Journal of Cloud Computing. 2026 Sep 30.
- Nicolazzo S, Nocera A, Pedrycz W. Service level agreements and security SLA: A comprehensive survey. arXiv preprint arXiv:2405.00009. 2024 Jan 31.
- Lella I, Tsekmezoglou E, Naydenov RS, Ciobanu C. European Union Agency for Cyber Security (ENISA) Threat Landscape. Jul. 2022 Jul.
- Lata S, Singh D. Intrusion detection system in cloud environment: Literature survey & future research directions. International Journal of Information Management Data Insights. 2022 Nov 1;2(2):100134.
- Eddermoug N, Mansour A, Azmi M, Sadik M, Sabir E, Bahassi H. A literature review on attacks prevention and profiling in cloud computing. Procedia Computer Science. 2023 Jan 1;220:970-7.
- Aldallal A, Alisa F. Effective intrusion detection system to secure data in cloud using machine learning. Symmetry. 2021 Dec 3;13(12):2306.
- Anitha Ruth J, Sirmathi H, Meenakshi A. Secure data storage and intrusion detection in the cloud using MANN and dual encryption through various attacks. IET Information Security. 2019 Jul;13(4):321-9.
- Cohen A, Nissim N. Trusted detection of ransomware in a private cloud using machine learning methods leveraging meta-features from volatile memory. Expert Systems with Applications. 2018 Jul 15;102:158-78.
- Arányi G, Miseta T, Szücs V. Ransomware detection based on server-side file operation logs using machine learning. Journal on Information Security. 2026 Mar 9;2026(1):8.
- Salih BM, Mohammad OK. Cloud data leakage, security, privacy issues and challenges. Procedia Computer Science. 2024 Jan 1;242:592-601.
- Pascoe CE. Public draft: The NIST cybersecurity framework 2.0. National Institute of Standards and Technology. 2023 Aug 7.
- Haufe K. Information Privacy Management-A. InProceedings of International Conference on Theoretical and Applied Computing: ICTAC 2024 2025 Feb 13 (p. 129). Springer Nature.
- Kumar R, Goyal R. Assurance of data security and privacy in the cloud: A three-dimensional perspective. Software Quality Professional. 2019 Mar 1;21(2):7-26.