PROTECTION OF CORPORATE DATABASES BASED ON RISK-ORIENTED ACCESS SEGMENTATION USING ARTIFICIAL INTELLIGENCE

Abstract

The article considers the problem of increasing the level of protection of corporate databases in the face of an
increasing number of complex multi-step attacks and internal threats. The limitations of traditional approaches to access
control, which are based on static policies and do not take into account the context of interaction between subjects in the
network, are analyzed. A method for protecting corporate databases based on risk-based access segmentation using
artificial intelligence is proposed, which is based on the representation of access processes in the form of a graph model.
Within the framework of the approach, the concept of a database access path is introduced and an integrated risk
assessment is formed, which takes into account the criticality of nodes, the probability of transitions and the structure of
interaction. Based on the obtained risk values, an adaptive response mechanism is implemented, which involves dynamic
updating of access policies, isolation of anomalous flows in quarantine segments of the network and blocking of
dangerous interaction scenarios. A feature of the proposed approach is the focus not on individual nodes or events, but on
holistic access paths, which allows for effective detection and neutralization of complex attacks, including lateral
movement and hidden behavioral anomalies. The use of artificial intelligence methods ensures the system's adaptability
to changes in user behavior and the dynamics of the network environment. Verification of the method in the training
environment and the obtained experimental results using the F1-score, FPR, ASR criteria confirm the effectiveness of the
proposed method of risk-based access segmentation, which provides increased accuracy in anomaly detection, reduced
proportion of successful attacks, and timely response to threats. The proposed approach can be integrated into modern
security monitoring systems (SIEM/SOC) and used to improve the effectiveness of protecting information resources of
corporate systems.
Keywords: cybersecurity, corporate databases, information protection, segmentation method, artificial
intelligence, graph access models.

References
1. Savchenko, V. A., & Shapovalenko, O. D. (2020a). The main areas of artificial intelligence technologies in
cybersecurity. Modern information security, 44(4), 6-11. https://doi.org/10.31673/2409-7292.2020.040611.
2. Mr. Jalindhar Banshi Kachule, Prof. Badrinath Bulepatil, Prof. Vishal Gejge & Prof. Atish Ashokrao Shriniwar.
(2025). AI for Database Security Anomaly Detection: Leveraging Machine Learning for Real-Time Threat Identification.
International Journal of Latest Technology in Engineering Management & Applied Science, 14(8), 1039–1045.
https://doi.org/10.51583/ijltemas.2025.1408000133.
3. Пелещак, І., & Футрик, Ю. (2025). Прогнозування часових рядів за допомогою нейромережі з
послідовно з'єднаними lstm блоками. Herald of Khmelnytskyi National University. Technical sciences, 347(1), 432–
441. https://doi.org/10.31891/2307-5732-2025-347-59.
4. Touil, H., El Akkad, N., Satori, K., Soliman, N. F., & El-Shafai, W. (2024). Efficient Braille Transformation
for Secure Password Hashing. IEEE Access, 1. https://doi.org/10.1109/access.2024.3349487.
5. Pan X., Obahiaghon A., Makar B., Wilson S., Beard C. (2024). Analysis of database security. Open Access
Library J. 11(04), 1–9.. URL: https://doi.org/10.4236/oalib.1111366.
6. Shchavinskyi, Y., & Budzynskyi, O. (2025). Analysis of current problems of security of corporate databases
in the conditions of modern infrastructure and ways to solution them. Cybersecurity: Education, Science, Technique,
3(27), 390–405. https://doi.org/10.28925/2663-4023.2025.27.726.
7. Савченко,В. А., Смолєв,Є. С., & Гамза,Д. Є.(2023). Методика виявлення аномалій взаємодії
користувачів з інформаційними ресурсами організації. Сучасний захист інформації, 4(56), 6–12.
https://doi.org/10.31673/2409-7292.2023.030101.
8. Reddy, C., Prabhagaran, S., & Vaid, A. (2025). Adaptive Anomaly Detection in Database Transactions:
Bridging Security Gaps with Reinforcement Learning. European Journal of Artificial Intelligence and Machine Learning,
4(2), 8–14. https://doi.org/10.24018/ejai.2025.4.2.53.
9. Raeiszadeh, M., Ebrahimzadeh, A., Glitho, R. H., Eker, J., & Mini, R. A. F. (2024). Real-Time Adaptive
Anomaly Detection in Industrial IoT Environments. IEEE Transactions on Network and Service Management, 1.
https://doi.org/10.1109/tnsm.2024.3447532.
10. Bajic, B., Rikalovic, A., Suzic, N., & Piuri, V. (2024). Toward a Human-Cyber-Physical System for Real-Time
Anomaly Detection. IEEE Systems Journal, 1–12. https://doi.org/10.1109/jsyst.2024.3402978.
11. Pujol-Perich, D., Suarez-Varela, J., Ferriol, M., Xiao, S., Wu, B., Cabellos-Aparicio, A., & Barlet-Ros, P.
(2021). IGNNITION: Bridging the Gap between Graph Neural Networks and Networking Systems. IEEE Network, 35(6),
171–177. https://doi.org/10.1109/mnet.001.2100266.
12. Zhong, M., Lin, M., Zhang, C., & Xu, Z. (2024). A survey on graph neural networks for intrusion detection
systems: Methods, trends and challenges. Computers & Security, 141, 103821. https://doi.org/10.1016/ j.cose.
2024.103821.
13. Caville, E., Lo, W. W., Layeghy, S., & Portmann, M. (2022). Anomal-E: A self-supervised network intrusion
detection system based on graph neural networks. Knowledge-Based Systems, 110030. https://doi.org/10.1016
/j.knosys.2022.110030.
14. Okdem, S., & Okdem, S. (2024). Artificial Intelligence in Cybersecurity: A Review and a Case Study. Applied
Sciences, 14(22), 10487. https://doi.org/10.3390/app142210487.
15. Шульга, В., Іванченко, Є., Берестяна, Т., & Шкурченко, О. (2025). Методи та моделі протидії груповим
кіберзагрозам на основі штучного інтелекту. Електронне фахове наукове видання «Кібербезпека: освіта, наука,
техніка», 2(30), 593–606. https://doi.org/10.28925/2663-4023.2025.30.998.
16. Xu H., Pang G., Wang Y., & Wang Y. (2023). Deep Isolation Forest for Anomaly Detection. IEEE Trans. on
Knowl. and Data Eng, 35(12), 12591–12604. https://doi.org/10.1109/TKDE.2023.3270293.
17. Lindemann, B., Maschler, B., Sahlab, N., & Weyrich, M. (2021). A survey on anomaly detection for technical
systems using LSTM networks. Computers in Industry, 131, 103498. https://doi.org/10.1016/j.compind.2021.103498.