Volume 14, Issue 10 · IJARST · ISSN 2319-1783 / 2320-1126

Behaviour-Aware Machine Learning Access Control for Detecting Unauthorized User Activities

Behaviour-Aware Machine Learning Access Control for Detecting Unauthorized User Activities is an open-access, peer-reviewed research paper by PAUL NDUDIRI OHIA, EMMANUEL WARIBO OTITI, published in Volume 14, Issue 10 of the International Journal of Advanced Research in Science and Technology (IJARST), a UGC-approved journal (Print ISSN 2319-1783, Online ISSN 2320-1126).

Author

PAUL NDUDIRI OHIA, EMMANUEL WARIBO OTITI

Abstract

Traditional access control systems normally decide whether a user is permitted to access a resource by checking identity, role, attribute, or policy rules. This approach is necessary but incomplete because unauthorized activity may be performed through a valid account after credential theft, privilege abuse, session hijacking, or insider misuse. This study developed and evaluated a behaviour-aware machine learning access control system for detecting unauthorized user activities within a web application environment. The completed system collects behaviour data during login and sensitive resource access, extracts model-ready features, applies Isolation Forest anomaly detection, calculates a risk score, and enforces adaptive access decisions. The implemented modules include authentication, user registration, behaviour collection, feature extraction, Isolation Forest model training and inference, risk scoring, access-decision enforcement, access-log storage, and an administrator monitoring dashboard. A synthetic behaviour-based web access log dataset was generated to represent Admin, Lecturer, and Student activities under both normal and suspicious conditions. The final demonstration database contained 693 access-log records, including 435 normal events and 258 anomalous events. The system produced five decision outcomes: Allow Access, Allow with Monitoring, Step-up Verification, Restricted Access, and Deny and Alert Admin. The result showed that behaviour-aware access control improves static authorization by checking not only whether a user is authorized, but whether the current behaviour is normal for that user context.

Keywords: Behaviour-Based Access Control, Machine Learning, Anomaly Detection, Isolation Forest, One-Class SVM, Autoencoder, Risk Score, Unauthorized Access

DOI: https://doi.org/10.62226/ijarst20262845

 

REFERENCES

[1] G. Folino, C. Otranto Godano, and F. S. Pisani, "An ensemble-based framework for user behaviour anomaly detection and classification for cybersecurity," The Journal of Supercomputing, vol. 79, pp. 11660-11683, 2023.

[2] M. Landauer, F. Skopik, G. Hold, and M. Wurzenberger, "A User and Entity Behavior Analytics Log Data Set for Anomaly Detection in Cloud Computing," in Proc. IEEE International Conference on Big Data, pp. 4285-4294, 2023.

[3] S. Aboukadri, A. Ouaddah, and A. Mezrioui, "Machine learning in identity and access management systems: Survey and deep dive," Computers & Security, vol. 139, article 103729, 2024.

[4] A. Bamberger and M. Fernandez, "Automated generation and update of structured ABAC policies," in Proc. ACM Workshop on Secure and Trustworthy Cyber-Physical Systems, pp. 31-40, 2024.

[5] S. Shang, X. Wang, and A. Liu, "ABAC policy mining method based on hierarchical clustering and relationship extraction," Computers & Security, vol. 139, article 103717, 2024.

[6] S. K. Bai, J. A. Goveas, and B. Mitra, "Enhancing Access Control in Distributed Systems Through Intelligent ABAC Policy Mining," in Proc. 22nd International Conference on Security and Cryptography, pp. 503-514, 2025.

[7] A. Biswas, B. Mitra, I. Gondal, and Q. Fu, "Securing Multi-Domain Systems: Intelligent ABAC Policy Learning for Cross-Domain Access Control," in Proc. 22nd Annual International Conference on Privacy, Security and Trust, 2025.

[8] V. C. Hu, D. R. Kuhn, D. F. Ferraiolo, and J. Voas, Attribute Considerations for Access Control Systems, NIST Special Publication 800-205, 2019.

[9] S. Rose, O. Borchert, S. Mitchell, and S. Connelly, Zero Trust Architecture, NIST Special Publication 800-207, 2020.

[10] F. T. Liu, K. M. Ting, and Z. H. Zhou, "Isolation Forest," in Proc. IEEE International Conference on Data Mining, pp. 413-422, 2008.

[11] D. Ni, H. Shi, Y. Chen, and J. Guo, "Attribute based access control based cross-domain access control in service-oriented architecture," in Proc. International Conference on Computer Science and Service System, pp. 1405-1408, 2012.

[12] O. Brdiczka, J. Liu, B. Price, J. Shen, A. Patil, R. Chow, E. Bart, and N. Ducheneaut, "Proactive insider threat detection through graph learning and psychological context," in Proc. IEEE Symposium on Security and Privacy Workshops, pp. 142-149, 2012.

DOI

10.62226/ijarst20262845

PAGES : 1663-1671 | 6 VIEWS | 2 DOWNLOADS

How do you cite this paper?

PAUL NDUDIRI OHIA, EMMANUEL WARIBO OTITI — “Behaviour-Aware Machine Learning Access Control for Detecting Unauthorized User Activities.” International Journal of Advanced Research in Science and Technology (IJARST), Volume 14, Issue 10. DOI: 10.62226/ijarst20262845.

Read / Download Full Article