Citation:

Jiwan Prakash Gupta , 2026. "An Intelligent Machine Learning Framework for Optimizing Identity and Access Management (IAM) Policies in Cloud Infrastructure ", ESP Journal of Engineering & Technology Advancements  6(1): 79-88.

Abstract:

Identity and Access Management (IAM) is an important factor in ensuring secure and effective access control in cloud computing environments. This work presents a sequential machine-learning-based model to optimize IAM policies using a high-dimensional Cloud Access Control Parameter Management dataset. The paradigm incorporates systematic preprocessing of data, feature engineering, label encoding, feature selection using Boruta, feature scaling, and hybrid data balancing, 80: 20 train -test split and 5-fold cross-validation. Together with various ML algorithms, such as Random Forest Classifier (RFC), LightGBM, Gradient Boosting Classifier (GBC), XGBoost, and a soft Voting ensemble, multiple machine learning models are trained and tested based on the standard performance metrics and ROC analysis. The experiment's findings show that the Voting Classifier has the best accuracy (98.19), followed by LightGBM (98.01), RFC (97.24), and XGBoost (90.95). The results indicate that ensemble-based and boosting models offer strong, precise, and generalized IAM security predictions, and hence the suggested framework could be effectively used to improve control over access to clouds and security policy issues.

References:

[1] A. Wairagade and S. Ranjan, “AI in Identity and Access Management (IAM) for Enterprise Systems: A Comparative Analysis,” Procedia Comput. Sci., vol. 263, pp. 167–174, 2025, doi: 10.1016/j.procs.2025.07.021.

[2] S. Amrale, “Proactive Resource Utilization Prediction for Scalable Cloud Systems with Machine Learning,” Int. J. Res. Anal. Rev., vol. 10, no. 4, pp. 758–764, 2023.

[3] S. K. Chintagunta, “Enhancing Cloud Database Security Through Intelligent Threat Detection and Risk Mitigation,” TIJER – Int. Res. J., vol. 9, no. 10, pp. 49–55, 2022.

[4] D. Patel, “Leveraging Blockchain and AI Framework for Enhancing Intrusion Prevention and Detection in Cybersecurity,” Tech. Int. J. Eng. Res., vol. 10, no. 6, 2023, doi: 10.56975/tijer.v10i6.158517.

[5] M. Menghnani, “Modern Full Stack Development Practices for Scalable and Maintainable Cloud-Native Applications,” Int. J. Innov. Sci. Res. Technol., vol. 10, no. 2, 2025, doi: 10.5281/zenodo.14959407.

[6] M. R. R. Deva, “Advancing Industry 4.0 with Cloud-Integrated Cyber-Physical Systems for Optimizing Remote Additive Manufacturing Landscape,” in 2025 IEEE North-East India International Energy Conversion Conference and Exhibition (NE-IECCE), IEEE, Jul. 2025, pp. 1–6. doi: 10.1109/NE-IECCE64154.2025.11182940.

[7] A. Parupalli and H. Kali, “An In-Depth Review of Cost Optimization Tactics in Multi-Cloud Frameworks,” Int. J. Adv. Res. Sci. Commun. Technol., vol. 3, no. 5, pp. 1043–1052, Jun. 2023, doi: 10.48175/IJARSCT-11937Q.

[8] P. Chandrashekar and M. Kari, “Design Machine Learning-Based Zero-Trust Intrusion Identification Models for Securing Cloud Computing System,” Int. J. Res. Anal. Rev., vol. 11, no. 4, pp. 901–907, 2024.

[9] S. Phalke, Y. D. Athave, and B. N. Ilag, “A Multi-Layered Approach to IT Infrastructure Governance and Compliance: Security, Hardening, and Audit Readiness,” Int. J. Comput. Appl., vol. 187, no. 12, p. 9, 2025, doi: 10.5120/ijca2025925133.

[10] G. Maddali, “An Efficient Bio-Inspired Optimization Framework for Scalable Task Scheduling in Cloud Computing Environments,” Int. J. Curr. Eng. Technol., vol. 15, no. 3, pp. 229–238, 2025.

[11] V. Shah, “Traffic Intelligence in IoT and Cloud Networks: Tools for Monitoring, Security, and Optimization,” Int. J. Recent Technol. Sci. Manag., vol. 9, no. 5, 2024, doi: 10.10206/IJRTSM.2025894735.

[12] V. Shewale, “Beyond EDR: Exploring the rise of XDR for unified threat detection and response,” World J. Adv. Eng. Technol. Sci., vol. 15, no. 2, pp. 380–386, May 2025, doi: 10.30574/wjaets.2025.15.2.0551.

[13] N. K. Prajapati, “Cloud-based serverless architectures: Trends, challenges and opportunities for modern applications,” World J. Adv. Eng. Technol. Sci., vol. 16, no. 1, pp. 427–435, Jul. 2025, doi: 10.30574/wjaets.2025.16.1.1225.

[14] A. Syed, AI-Powered Threat Detection and Mitigation. 2024.

[15] C. B. Bora, J. Silva Weber, and N. Zincir-Heywood, “Network Identity Management: Application, Action and Device Aware Monitoring,” in 2025 IEEE 49th Annual Computers, Software, and Applications Conference (COMPSAC), IEEE, Jul. 2025, pp. 2269–2274. doi: 10.1109/COMPSAC65507.2025.00319.

[16] A. AbouElabbas, A. H. Abdel-Gawad, and Y. Fahmy, “A Tabular Deep Learning Approach for Access Control Using TabNet,” in 2025 7th Novel Intelligent and Leading Emerging Sciences Conference (NILES), IEEE, Oct. 2025, pp. 134–138. doi: 10.1109/NILES68063.2025.11231988.

[17] H. B. Demirsoy, E. N. Kose, F. Aydogan, M. H. Ezgin, and M. A. Akcayol, “Hybrid Deep Learning Model Based Advanced AI-Driven Identity and Access Management System for Enhanced Security and Efficiency,” in 2024 8th International Symposium on Innovative Approaches in Smart Technologies (ISAS), IEEE, Dec. 2024, pp. 1–4. doi: 10.1109/ISAS64331.2024.10845215.

[18] H. Sivaraman, “Zero Trust Identity and Access Management (IAM) in Multi-Cloud Environments,” ESP J. Eng. Technol. Adv., vol. 3, no. 2, pp. 135–139, 2023, doi: 10.56472/25832646/JETA-V3I6P108.

[19] T. Van Ede, N. Khasuntsev, B. Steen, and A. Continella, “Detecting Anomalous Misconfigurations in AWS Identity and Access Management Policies,” in CCSW 2022 - Proceedings of the 2022 Cloud Computing Security Workshop, co-located with CCS 2022, 2022. doi: 10.1145/3560810.3564264.

[20] S. Chatterjee, “A Data Governance Framework for Big Data Pipelines: Integrating Privacy, Security, and Quality in Multitenant Cloud Environments,” Tech. Int. J. Eng. Res., vol. 10, no. 5, 2023, doi: 10.56975/tijer.v10i5.158181.

[21] M. Mehmood, R. Amin, M. M. A. Muslam, J. Xie, and H. Aldabbas, “Privilege Escalation Attack Detection and Mitigation in Cloud Using Machine Learning,” IEEE Access, vol. 11, 2023, doi: 10.1109/ACCESS.2023.3273895.

[22] G. Sarraf and V. Pal, “Autonomous Threat Detection and Response in Cloud Security: A Comprehensive Survey of AI-Driven Strategies,” Int. J. Emerg. Res. Eng. Technol., vol. 6, no. 4, 2025, doi: 10.63282/3050-922X.IJERET-V6I4P114.

[23] S. Srinivasan, R. Sundaram, K. Narukulla, S. Thangavel, and S. B. Venkata Naga, “Cloud-Native Microservices Architectures: Performance, Security, and Cost Optimization Strategies,” Int. J. Emerg. Trends Comput. Sci. Inf. Technol., vol. 4, no. 1, pp. 16–24, 2023, doi: 10.63282/3050-9246.ijetcsit-v4i1p103.

[24] V. Verma, “Big Data and Cloud Databases Revolutionizing Business Intelligence,” TIJER – Int. Res. J., vol. 9, no. 1, 2022.

[25] S. Narang and A. Gogineni, “Zero-Trust Security in Intrusion Detection Networks: An AI-Powered Threat Detection in Cloud Environment,” Int. J. Sci. Res. Mod. Technol., vol. 4, no. 5, pp. 60–70, Jun. 2025, doi: 10.38124/ijsrmt.v4i5.542.

[26] I. Bansal, “Digital Transformation using Artificial Intelligence and Machine Learning for Secure Enterprises for Secure Enterprise Applications: A Framework using Cloud IAM Security,” Int. J. Intell. Syst. Appl. Eng., vol. 11, no. 11s, pp. 815–821, 2023.

[27] K. C. Wannere, “AI-Augmented Threat Detection and Policy Drift Remediation in Hybrid Cloud Network Security Architectures,” Int. J. Eng. Res. Technol., vol. 14, no. 05, 2025.

[28] B. Rajak, N. Kumaresh, N. K. Hamid, M. B. Alazzam, S. I. Hassan, and S. V, “AI-Driven Anomaly Detection for Secure Identity and Access Management in Cloud Platform,” in 2025 Global Conference in Emerging Technology (GINOTECH), IEEE, May 2025, pp. 1–5. doi: 10.1109/GINOTECH63460.2025.11076807.

Keywords:

IAM, Cloud, Voting Classifier, Artificial Intelligence, Machine Learning.