AI-Assisted Cloud Security Framework For Intrusion Detection, Threat Intelligence, and Real-Time Anomaly Prediction

K Hema; R Mogesh; N Adarsh Naga Siva; K Mohini; A Muni Sai Chandu

doi:10.5281/zenodo.18996613

Authors

K Hema Department of CSE, Siddharth Institute of Engineering and Technology, Puttur, A.P, India.
R Mogesh Department of CSE (Cloud Computing), Siddharth Institute of Engineering and Technology, Puttur, A.P, India.
N Adarsh Naga Siva Department of CSE (Cloud Computing), Siddharth Institute of Engineering and Technology, Puttur, A.P, India.
K Mohini Department of CSE (Cloud Computing), Siddharth Institute of Engineering and Technology, Puttur, A.P, India.
A Muni Sai Chandu Department of CSE (Cloud Computing), Siddharth Institute of Engineering and Technology, Puttur, A.P, India.

DOI:

https://doi.org/10.5281/zenodo.18996613

Keywords:

AI-assisted cloud security, intrusion detection, anomaly prediction, hybrid AI model, Logistic Regression, Decision Trees, Isolation Forest, threat intelligence

Abstract

The rapid development and deployment of cloud computing services have totally changed the paradigm of how data is managed and applications are delivered. However, the highly dynamic nature of cloud computing infrastructure is prone to various security risks. The traditional security devices, such as rule-based firewalls and signature-based intrusion detection systems, are not effective in countering the complex nature of cyber threats. In this paper, we propose an AI-based framework that provides intelligent intrusion detection and real-time prediction of anomalies in the cloud computing infrastructure. The proposed framework is based on a hybrid AI model that incorporates various AI algorithms, such as Logistic Regression, Decision Trees, Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN), and Isolation Forest, to name a few. The framework provides real-time monitoring and intrusion detection, thus protecting the cloud computing infrastructure from various potential threats. The proposed framework provides high accuracy in intrusion detection, reaching up to 99.47% accuracy, 99.69% precision, and 99.43% F1-score, thus demonstrating the effectiveness of the proposed model. This work highlights the need to design adaptive, scalable, and intelligent security devices to counter the changing nature of cloud computing security threats.

References

Cantero, B., Zalazar, B., Pezzini, B., Gaitán, C., Bertucci, C., & Mazzanti, C. (2026). Machine learning based anomaly detection for multi-cloud security monitoring. ResearchGate.

Govindarajan, V. (2026). An advanced AI-driven framework for intelligent security risk detection using hybrid mechanisms. SN Applied Sciences.

Mathivanan, N. (2026). An integrated methodology for intrusion detection and zero trust security in cloud environments. Journal of Cloud Computing.

Singh, R., Kumar, A., & Mishra, S. (2025). Attentional LSTM-ensemble architecture for intrusion detection. Scientific Reports, 15(3).

Dissanayake, N., & Thayasivam, U. (2025). Attack-specialized deep learning with ensemble fusion for network anomaly detection. arXiv preprint.

Alhusseini, M. M., Rouhi, A., & Feizi-Derakhshi, M. R. (2026). AI-powered hybrid intrusion detection framework for cloud security using metaheuristic optimization. arXiv preprint.

Saraswathi, S. (2025). Hybrid anomaly detection model integrating LSTM and isolation forest for enhanced performance. In Proceedings of the International Conference on Inventive Research in Computing Applications (ICIRCA).

Kumar, A. (2025). Impact of machine learning on intrusion detection and anomaly detection. Information, 16(7).

Ferozuddin, F. (2025). AI-driven anomaly detection model for intrusion detection. International Journal of Computer Applications, 187(6).

Evaluation of anomaly-based network intrusion detection systems. (2025). Security Journal.

Anomaly detection in heterogeneous cybersecurity data. (2025). Fraud Analytics and Optimization.

Cybersecurity in cloud computing: AI-driven intrusion detection and mitigation strategies. (2025). IEEE Access (Accepted for publication).

Andrés, P., Ivanov, I., & Wang, Z. (2025). Real-time AI-based threat intelligence for cloud security enhancement. Innovative: International Multi-disciplinary Journal of Applied Technology, 3(3), 36–54.

Singh, H. (2025). Enhancing cloud security posture with AI-driven threat detection and response mechanisms. SSRN Electronic Journal.

Afraji, D. M. A. A., Lloret, J., & Peñalver, L. (2025). Deep learning-driven defense strategies for mitigating DDoS attacks in cloud computing environments. Cyber Security and Applications, 3, 100085.

He, Q., Zhang, Y., Xu, A., Ye, Z., Zhou, W., Lin, Q., & Zhang, T. (2026). LSTM-1DResNet: An intrusion detection model for connected and autonomous vehicles based on deep learning. IEEE Transactions on Vehicular Technology.

Srinivasan, M., & Senthilkumar, N. C. (2025). Intrusion detection and prevention system (IDPS) model for IIoT environments using hybridized framework. IEEE Access, 13, 26608–26621.

Nagamani, S., Arivalagan, S., Senthil, M., & Sudhakar, P. (2025). Horse herd optimization with deep learning-based intrusion detection in cloud computing environment. International Journal of Information Technology, 17(1), 387–393.

Govindrajan, V. (2025). Machine learning-based approach for handling imbalanced data for intrusion detection in the cloud environment. In Proceedings of the 3rd International Conference on Disruptive Technologies (ICDT) (pp. 810–815).

Alamir, R. H., Noor, A., Almukhalfi, H., Almukhlifi, R., & Noor, T. H. (2025). SecFedDNN: A secure federated deep learning framework for edge–cloud environments. Systems, 13(6), 463.

Yu, T., Huang, W., Tang, X., & Zheng, D. (2025). A hybrid unsupervised machine learning model with spectral clustering and semi-supervised support vector machine for credit risk assessment. PLOS ONE, 20(1), e0316557.

Haider, Z. A., Zeb, A., Rahman, T., Khan, F. M., Khan, I. U., Sohail, Q., Bilal, H., Khan, M. A., & Ullah, I. (2025). Optimizing cloud security with a hybrid BiLSTM-BiGRU model for efficient intrusion detection. ICCK Transactions on Sensing, Communication, and Control, 2(2), 106–121.

Ahmad, S., Arif, M., Mehfuz, S., Ahmad, J., & Nazim, M. (2025). Deep learning-based cloud security: Innovative attack detection and privacy-focused key management. IEEE Transactions on Computers.

Arun, M., Barik, D., Othman, N. A., Praveenkumar, S., & Tudu, K. (2025). Investigating the performance of AI-driven smart building systems through advanced deep learning model analysis. Energy Reports, 13, 5885–5899.

Jiang, X., Jia, R., & Zhang, F. (2025). Deep learning-based user behavior anomaly detection and threat early warning in cloud computing environments. Academia Nexus Journal, 4(3).

Rout, C., Sethi, S., Badajena, J. C., & Sahoo, R. K. (2026). FSEGM: Feature selection and ensemble generative model for adaptive cloud security. Journal of Cloud Computing, 27(1), 6.

Hanisha, V., & Mohan, M. (2026). A hybrid ensemble model for intrusion detection in cloud environment with transparent and explainable AI techniques. In Recent advances in computational methods in science and technology (pp. 28–33). Boca Raton, FL: CRC Press.

Ahmed, S. T., Basha, S. M., Ramachandran, M., Daneshmand, M., & Gandomi, A. H. (2023). An edge-AI-enabled autonomous connected ambulance-route resource recommendation protocol (ACA-R3) for eHealth in smart cities. IEEE Internet of Things Journal, 10(13), 11497-11506.

Ahmed, S. T., & Fathima, A. S. (2024). Medical ChatBot assistance for primary clinical guidance using machine learning techniques. Procedia Computer Science, 233, 279-287.

Periasamy, K., Periasamy, S., Velayutham, S., Zhang, Z., Ahmed, S. T., & Jayapalan, A. (2022). A proactive model to predict osteoporosis: An artificial immune system approach. Expert Systems, 39(4), e12708.