Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM68362
Volume:
10 |
10 |
Oct 2026
Pages:
1-6
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
Computer Engineering
Sandip Institute Of Technology and Research Centre ,Nashik
Computer Engineering
Sandip Institute Of Technology and Research Centre ,Nashik
Computer Engineering
Sandip Institute Of Technology and Research Centre ,Nashik
Computer Engineering
Sandip Institute Of Technology and Research Centre ,Nashik
Computer Engineering
Sandip Institute Of Technology and Research Centre ,Nashik
Role-Based Access Control (RBAC) has been the leading access control model for a long time due to its simplicity and ease of administration. However, the creation of contemporary computing environments has revealed its limitations in dealing with dynamic and context-aware authorization requirements. Attribute-Based Access Control (ABAC) offers more flexibility since access decisions are based on multiple attributes. Nonetheless, the transition from RBAC to ABAC remains complex and costly. Some recent works have studied supervised learning approaches to automate ABAC policy mining, to reduce the manual efforts while improving the policy accuracy. This review paper offers an in-depth analysis of the existing supervised learning based approaches for mining ABAC policies from RBAC enabled systems. It reviews the machine learning algorithms, feature extraction methods, datasets, evaluation metrics and policy generation strategies that are commonly used in recent studies. The literature review indicates that supervised learning can potentially enhance the efficiency and scalability of RBAC-to-ABAC migration. However, there are still some open research issues including limited labeled datasets, feature selection, policy interpretability and model generalization. This review aims to review the current state of the research, identify existing gaps, and discuss future research directions for developing intelligent and scalable ABAC policy mining solutions.
KEYWORDS
The proposed work proposes a supervised learning based approach to mine ABAC rules from an existing RBAC-enabled system. The approach leverages existing user, role, permission and access-decision information to reduce manual policy creation and to provide more flexible and fine-grained access control. Future work can be done to improve the system by trying different machine-learning algorithms, larger real world datasets, deep learning and explainable AI, real-time policy update and automatic conflict resolution.
[1] M. Alohaly, O. Balogun and D. Takabi, “Integrating Cyber Deception Into Attribute-Based Access Control (ABAC) for Insider Threat Detection,” IEEE Access, vol. 10, pp. 108965–108978, 2022, doi: 10.1109/ACCESS.2022.3213645. [2] H. Kim, D.-K. Kim and A. Alaerjan, “ABAC-Based Security Model for DDS,” IEEE Transactions on Dependable and Secure Computing, vol. 19, no. 5, pp. 3113–3124, Sept.–Oct. 2022, doi: 10.1109/TDSC.2021.3085475. [3] C. Cotrini, T. Weghorn and D. Basin, “Mining ABAC Rules from Sparse Logs,” 2018 IEEE European Symposium on Security and Privacy (EuroS&P), London, UK, 2018, pp. 31–46, doi: 10.1109/EuroSP.2018.00011. [4] L. Karimi, M. Aldairi, J. Joshi and M. Abdelhakim, “An Automatic Attribute-Based Access Control Policy Extraction From Access Logs,” IEEE Transactions on Dependable and Secure Computing, vol. 19, no. 4, pp. 2304–2317, July–Aug. 2022, doi: 10.1109/TDSC.2021.3054331. [5] F. Shan, J. Liu, X. Wang, W. Liu and B. Zhou, “A Smart Access Control Method for Online Social Networks Based on Support Vector Machine,” IEEE Access, vol. 8, pp. 11096–11103, 2020, doi: 10.1109/ACCESS.2020.2963932. [6] B. Bera, A. K. Das, M. S. Obaidat, P. Vijayakumar, K.-F. Hsiao and Y. Park, “AI-Enabled Blockchain-Based Access Control for Malicious Attacks Detection and Mitigation in IoE,” IEEE Consumer Electronics Magazine, vol. 10, no. 5, pp. 82–92, Sept. 2021, doi: 10.1109/MCE.2020.3040541. [7] C. Wang et al., “An Interpretable and Accurate Deep-Learning Diagnosis Framework Modeled With Fully and Semi-Supervised Reciprocal Learning,” IEEE Transactions on Medical Imaging, vol. 43, no. 1, pp. 392–404, Jan. 2024, doi: 10.1109/TMI.2023.3306781. [8] Y. Luo, Q. Shen and Z. Wu, “Casbin: A Graph-Based Approach for Efficient and Verifiable Cloud Authorization,” IEEE Transactions on Dependable and Secure Computing, preprint, 2026, doi: 10.1109/TDSC.2026.3709803. [9] Y. An, H. Xue and X. Zhao, “Conditional Self-Supervised Learning for Few-Shot Learning,” IEEE Transactions on Circuits and Systems for Video Technology, vol. 36, no. 7, pp. 9794–9807, July 2026, doi: 10.1109/TCSVT.2026.3670944. [10] X. Wang, D. Kihara, J. Luo and G.-J. Qi, “EnAET: A Self-Trained Framework for Semi-Supervised and Supervised Learning With Ensemble Transformations,” IEEE Transactions on Image Processing, vol. 30, pp. 1639–1647, 2021, doi: 10.1109/TIP.2020.3044220.
Publication Date
10/26/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
2
Total views since publication
PDF Downloads
5
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...