Raqamli Transformatsiya va Sun’iy Intellekt
AN INTELLIGENT MODEL FOR ASSESSING CYBER RISKS BASED ON USER BEHAVIOR IN INFORMATION SYSTEMS
1 International Islamic Academy of Uzbekistan
Zenodo DOI: 10.5281/zenodo.23617791
Keywords
Abstract
Modern information systems generate heterogeneous traces of user activity, while conventional security controls frequently evaluate events independently and rely on static thresholds. This study proposes an intelligent model for assessing cyber risks from user behavior by integrating behavioral deviations, access context, resource sensitivity, anomaly severity, and historical compliance into a normalized risk score. The model separates feature extraction, adaptive weighting, risk aggregation, and security-action recommendation. A contextual weighting mechanism is introduced to avoid assigning identical importance to behavioral indicators under different access conditions. The analytical assessment uses controlled user-activity scenarios to examine the sensitivity of the model to changes in behavioral and contextual factors. The results show that the proposed structure produces monotonic risk growth when high-impact indicators change in an adverse direction and reduces the probability of excessive responses to isolated low-impact anomalies. The model is intended as a decision-support layer that complements, rather than replaces, conventional authentication, access control, logging, and endpoint security mechanisms.
References
- Liu, F. T., Ting, K. M., & Zhou, Z.-H. (2008). Isolation forest. In Proceedings of the 8th IEEE International Conference on Data Mining (pp. 413–422). IEEE.
- ISO/IEC 27005:2022. Information security, cybersecurity and privacy protection: Guidance on managing information security risks. International Organization for Standardization.
- Mishra, A., Vedula, V., Mishra, A., & Sharma, S. (2026). Artificial intelligence for cybersecurity: A scoping survey of paradigms, applications, and emerging trends. Algorithms, 19(8), Article 653.
- Paul, A., Sadiq, B. O., Buhari, D., & Olaniyan, R. (2025). A review of neural networks for enhanced user entity behavior analytics in cybersecurity: Addressing the challenge of vanishing gradient. International Journal of Research and Innovation in Applied Science, 9(12), 154–172.
- Tuor, A., Kaplan, S., Hutchinson, B., Nichols, N., & Robinson, S. (2017). Deep learning for unsupervised insider threat detection in structured cybersecurity data streams. In Proceedings of the AAAI-17 Workshop on Artificial Intelligence for Cyber Security.
- Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems 30 (pp. 4765–4774).
- Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). “Why should I trust you?”: Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (pp. 1135–1144). ACM.
- Hussain, H., & Kiani, A. A. (2026). Explainable behavioral analytics for users and entities using hybrid AI models: A MUEBA-XAI framework integrating LSTM, Isolation Forest, SHAP, and LIME. International Journal of Innovations in Science & Technology, 8(6), 2629–2648.
- Caputo, D., Stephens, G., Stephenson, B., and Kim, M. (2010). Human Behavior, Insider Threat, and Awareness: An Empirical Study of Insider Threat Behavior. MITRE Corporation.
- Dahle, N., Tumlin, A., Tran, N., Koutsoukos, X., & Derr, T. (2026). RAD: Rule-augmented relational anomaly detection. In Proceedings of the 35th ACM International Conference on Information and Knowledge Management (CIKM ’26), pp. 112–121. ACM.
- Chandola, V., Banerjee, A., & Kumar, V. (2009). Anomaly detection: A survey. ACM Computing Surveys, 41(3), Article 15.
- Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32.
- Maybury, M., Chase, P., Cheikes, B., et al. (2005). Analysis and Detection of Malicious Insiders. MITRE/ARDA.
- Hunker, J., & Probst, C. W. (2011). Insiders and insider threats: An overview of definitions and mitigation techniques. Journal of Wireless Mobile Networks, Ubiquitous Computing, and Dependable Applications, 2(1), 4–27.
- Komka, M. C., Ademuwagun, A. K., Abdullahi, S. M., Mashkur, T. M., & Ifeanyi, F. D. (2026). Proactive insider threat detection in cloud environment using machine learning. Nature Journal of Emerging Sciences, Technologies, and Innovations, 8(4), 397–410.
- Glasser, J., & Lindauer, B. (2013). Bridging the gap: A pragmatic approach to generating insider threat data. In Proceedings of the IEEE Security and Privacy Workshops (pp. 98–104). IEEE.
- Rose, S., Borchert, O., Mitchell, S., & Connelly, S. (2020). Zero Trust Architecture (NIST Special Publication 800-207). National Institute of Standards and Technology.
- Le, D. C., & Zincir-Heywood, N. (2021). Anomaly detection for insider threats using unsupervised ensembles. IEEE Transactions on Network and Service Management, 18(2).
- Joint Task Force Transformation Initiative. (2012). Guide for Conducting Risk Assessments (NIST Special Publication 800-30, Revision 1). National Institute of Standards and Technology.
- Cappelli, D. M., Moore, A. P., & Trzeciak, R. F. (2012). The CERT Guide to Insider Threats: How to Prevent, Detect, and Respond to Information Technology Crimes. Addison-Wesley.
- Strom, B., Battaglia, J., Kemmerer, M., et al. (2017). Finding Cyber Threats with ATT&CK-Based Analytics. MITRE.