Recent trends in AI- driven intrusion detection system for cloud computing and IoT: A systematic review
DOI:
https://doi.org/10.29070/p2qnb664Keywords:
Artificial Intelligence, Cloud Computing, Machine Learning, Cybersecurity, Federated Learning, Explainable AIAbstract
The cloud and IoT environments are always changing, creating increasingly complex and large cyber security threats. Therefore more sophisticated and adaptable security solutions are required. Intrusion Detection Systems (IDS) are important parts of the network security solution, but signature and rule based IDSs are not capable of detecting complex, zero day attacks. When it comes to intrusion detection systems (IDS), artificial intelligence (AI) is crucial since it forms the basis of their capabilities. For enhanced accuracy and agility in detecting assaults, IDS is using ML algorithms, DL, and hybrid techniques. This systematic analysis examines the published scenarios from 2019 to 2026 in order to delve into the most recent advancements in cloud and IoT intrusion detection systems (IDS) that are based on AI technology. A systematic literature search (SLS) aims to locate, choose and assess relevant literature from large academic databases and is grounded on the principle of systematic literature reviews (SLR). In this study, the authors use common ML measures including F1-score, recall, accuracy, and precision to assess how well various previous methods performed. They further categorise these methods as either ML-based, DL-based, or hybrid. Addressing key constraints such as data imbalance, computing expenditures, and real-world application is also highlighted in the paper, along with the significance of ubiquitous datasets, cutting-edge models like federated learning, explainable AI, and lightweight models at the edge. Even if deep learning models can beat the competition, using them in IoT systems with limited resources is still a challenge. To cope with the evolving cyber-security threats in modern distributed systems, the article concludes that scalable, efficient, and privacy-preserving intrusion detection system (IDS) frameworks are crucial.
Downloads
References
1. Kikissagbe, B. R., & Adda, M. (2024). Machine learning-based intrusion detection methods in IoT systems: A comprehensive review. Electronics, 13(18), 3601.
2. Saied, M., Guirguis, S., & Madbouly, M. (2024). Review of artificial intelligence for enhancing intrusion detection in the Internet of Things. Engineering Applications of Artificial Intelligence, 107231.
3. Bar, S., Prasad, P. W. C., & Sayeed, M. S. (2024). Enhancing Internet of Things intrusion detection using artificial intelligence. Computers, Materials & Continua, 81(1), 1–23.
4. Vyas, A., Lin, P. C., Hwang, R. H., & Tripathi, M. (2024). Privacy-preserving federated learning for intrusion detection in IoT environments: A survey. IEEE Access, 12, 127018–127050.
5. Chelghoum, M., Bendiab, G., Labiod, M. A., Benmohammed, M., Shiaeles, S., & Mellouk, A. (2024). Blockchain and AI for collaborative intrusion detection in 6G-enabled IoT networks. IEEE Conference Proceedings.
6. Sharma, B., Sharma, L., Lal, C., & Roy, S. (2024). Explainable artificial intelligence for intrusion detection in IoT networks: A deep learning-based approach. Expert Systems with Applications.
7. Abdul Wahab, O. (2022). Intrusion detection in the IoT under data and concept drifts: Online deep learning approach. IEEE Internet of Things Journal, 9(20), 19706–19716.
8. Goranin, N., Hora, S. K., & Čenys, A. (2024). A bibliometric review of intrusion detection research in IoT: Evolution, collaboration, and emerging trends. Electronics, 13(16), 3210.
9. Ferrag, M. A., Maglaras, L., & Janicke, H. (2020). Deep learning for cyber security intrusion detection: Approaches, datasets, and comparative study. Journal of Information Security and Applications, 50, 102419.
10. Al-Garadi, M. A., Mohamed, A., Al-Ali, A. K., Du, X., Ali, I., & Guizani, M. (2020). A survey of machine and deep learning methods for Internet of Things security. IEEE Communications Surveys & Tutorials, 22(3), 1646–1685.
11. Vinayakumar, R., Soman, K. P., & Poornachandran, P. (2019). Applying deep learning approaches for network intrusion detection. IEEE Access, 7, 41525–41550.
12. Moustafa, N., & Slay, J. (2019). UNSW-NB15: A comprehensive data set for network intrusion detection systems. MilCIS Conference Proceedings, 1–6.
13. Koroniotis, N., Moustafa, N., Sitnikova, E., & Turnbull, B. (2019). Towards the development of realistic botnet dataset in the Internet of Things. Future Generation Computer Systems, 100, 779–796.
14. Mahmud, M. Z., Islam, S., Alve, S. R., & Pial, A. J. (2024). Optimized IoT intrusion detection using machine learning techniques. arXiv preprint.
15. Gueriani, A., Kheddar, H., & Mazari, A. C. (2024). Deep reinforcement learning for intrusion detection in IoT: A survey. arXiv preprint.
16. Pooja Soni and Sanjay Gour (2026), Artificial Intelligence and Machine Learning in Cybersecurity: A Review of Trends, Challenges, and Applications, Journal of Smart Sensors and Computing, 2(1), 1-23.
17. Chauhan, M., Gaur, S. (2026). A Hybrid Machine Learning Framework for Proactive Threat Detection in Cybersecurity Using Intelligent Feature Selection. In: Choudrie, J., Tuba, E., Perumal, T., Joshi, A. (eds) ICT for Intelligent Systems. ICTIS 2025. Smart Innovation, Systems and Technologies, vol 124. Springer, Singapore. https://doi.org/10.1007/978-981-95-1353-6_49
This work is licensed under a 