Dual-Edged Intelligence: AI-Driven Risk Management for Hybrid-Cloud Compute Environments
Abstract
Hybrid-cloud infrastructures combine on-premises and public-cloud resources to deliver agility and scale, but they also introduce novel security, compliance, and operational risks. We propose Dual-Edged Intelligence, a unified AI-driven framework that continuously profiles, predicts, and mitigates threats across virtual machines, containers, and serverless services in multi-cloud operations. Our approach layers supervised classification, unsupervised anomaly detection, and graph-based lateral-movement analysis into an ensemble scoring model. We implement a fully automated end to end pipeline starting from data collection through real-time remediation by using standard DevOps tooling. In a 10-node Kubernetes, Dual-Edged Intelligence reduced detection latency by 35%, cut false positives by 30%, and improved automated remediation success to 95% versus rule-based baselines.
Article Information
Journal |
International Journal of Advanced Engineering Science and Information Technology (IJAESIT) |
|---|---|
Volume (Issue) |
Vol. 8 No. 2 (2025): International Journal of Advanced Engineering Science and Information Technology (IJAESIT) |
DOI |
|
Pages |
16088-16092 |
Published |
April 8, 2025 |
| Copyright | |
Open Access |
This work is licensed under a Creative Commons Attribution 4.0 International License. |
How to Cite |
Amar Gurajapu, Swapna Anumolu, Vardhan Garimella, Venkata Manikanta Sai Ramakrishna Chundi, Venkata Sita Anand Prakash Gubbala (2025). Dual-Edged Intelligence: AI-Driven Risk Management for Hybrid-Cloud Compute Environments. International Journal of Advanced Engineering Science and Information Technology (IJAESIT) , Vol. 8 No. 2 (2025): International Journal of Advanced Engineering Science and Information Technology (IJAESIT) , pp. 16088-16092. https://doi.org/10.15662/IJAESIT.2025.0802003 |
References
2. Hamilton, A. (2020). Graph-based lateral-movement detection in enterprise environments. IEEE Security & Privacy, 18(3), 54–63. https://doi.org/10.1109/MSEC.2020.2978876
3. Kumar, V., & Lee, S. (2019). Configuration drift detection in IaC workflows. Journal of Cloud Computing, 8(1), 15–28. https://doi.org/10.1186/s13677-019-0148-2
4. Li, Y., Zhang, T., & Wu, J. (2022). Time-series anomaly detection in cloud metrics using LSTM autoencoders. ACM Transactions on Cyber-Physical Systems, 6(4), 1–22. https://doi.org/10.1145/3511234
5. Nguyen, P., Tran, D., & Le, H. (2020). API abuse patterns in multi-cloud environments. Proceedings of the ACM Symposium on Cloud Computing, 45–57. https://doi.org/10.1145/3419111.3421312
6. Patel, M., Chen, L., & Shannon, C. (2021). Workload anomaly characterization in hybrid clouds. Future Generation Computer Systems, 115, 316–330. https://doi.org/10.1016/j.future.2020.09.023
7. Xie, Q., & Zhao, L. (2018). Supervised intrusion detection with gradient boosting. International Journal of Information Security, 17(5), 527–539. https://doi.org/10.1007/s10207-018-0408-1