To obtain access to full text of journal and articles you must register!
- Article name
- Methodology for detecting anomalies in the access control system of the electronic information and educational environment of a higher educational institution
- Authors
- Arkhipov A. I., , arhip.09@ya.ru, Krasnodar Higher Military School named after General of the Army S. M. Shtemenko, Krasnodar, Russia
- Keywords
- anomaly detection / electronic information and educational environment / machine learning / cybersecurity
- Year
- 2025 Issue 2 Pages 16 - 24
- Code EDN
- VAUZSL
- Code DOI
- 10.52190/2073-2600_2025_2_16
- Abstract
- The necessity of an integrated approach that accounts for the heterogeneous information systems comprising the Electronic Information and Educational Environment (EIEE) is substantiated. A structural monitoring scheme has been developed. The feature space for the EIEE access-control system was formed on the basis of a global access matrix containing data from various subsystems. Pearson correlation analysis and feature-importance assessment were carried out. The study found that the LightGBM method provides the best anomaly-detection performance for the EIEE access-control system, achieving an accuracy of 96.18 %. Model quality was evaluated using the ROC curve, and stratified five-fold cross-validation with Bayesian hyper parameter optimization was performed.
- Text
- BUY for read the full text of article
- Buy
- 500.00 rub
