INTELLIGENT ADAPTIVE CYBER THREAT DETECTION SYSTEM BASED ON HYBRID ANALYSIS, FUZZY LOGIC, AND NEURAL NETWORKS
DOI:
https://doi.org/10.28925/2663-4023.2026.35.1416Keywords:
cyber threats; intrusion detection system; hybrid analysis; fuzzy logic; neural networks; information security; adaptive decision-making; machine learning; network traffic; intelligent system.Abstract
The article investigates the problem of improving the efficiency of cyber threat detection in modern intelligent information systems under conditions of increasing complexity of network attacks, dynamic network environments, and growing volumes of network traffic. The relevance of using intelligent methods for cyber event analysis to ensure adaptive response to modern cyber threats, including zero-day attacks, DDoS attacks, network anomalies, and modified intrusion types, is substantiated. An analysis of modern signature-based, anomaly-based, and hybrid intrusion detection systems is carried out, and their main shortcomings are identified, including a high level of false positives, insufficient adaptability, and limited capabilities for detecting new attack types. The paper proposes the architecture of an intelligent adaptive cyber threat detection system that combines signature-based and anomaly-based analysis with fuzzy logic and neural network mechanisms within a unified decision-making model. The system architecture includes modules for network traffic collection and preprocessing, feature vector generation, signature-based and anomaly-based analysis, fuzzy risk assessment, neural network analysis, result integration, and adaptive decision-making. A mathematical model for integrated cyber threat assessment based on adaptive weighted combination of the results of different analysis subsystems is developed. A mechanism for dynamic adjustment of weighting coefficients depending on network traffic characteristics, risk level, and cyber threat type is proposed. The practical significance of the obtained results lies in the possibility of using the proposed system to ensure cybersecurity of corporate networks, cloud platforms, automated control systems, and IoT environments.
Downloads
References
Ishaque, M., Md Johar, M. G., Khatibi, A., & Yamin, M. (2023). A novel hybrid technique using fuzzy logic, neural networks and genetic algorithm for intrusion detection system. Measurement: Sensors, 30, 100933. https://doi.org/10.1016/j.measen.2023.100933
Qazi, E. U. H., Faheem, M. H., & Zia, T. (2023). HDLNIDS: Hybrid deep-learning-based network intrusion detection system. Applied Sciences, 13(8), 4921. https://doi.org/10.3390/app13084921
Hnamte, V., & Hussain, J. (2023). DCNNBiLSTM: An efficient hybrid deep learning-based intrusion detection system. Telematics and Informatics Reports, 10, 100053. https://doi.org/10.1016/j.teler.2023.100053
Rahman, M. M., Shakil, S. A., & Mustakim, M. M. (2024). A survey on intrusion detection system in IoT networks. Cyber Security and Applications, 3, 100082. https://doi.org/10.1016/j.csa.2024.100082
Alnasser, O., Al Muhtadi, J., Saleem, K., & Shrestha, S. (2025). Signature and anomaly based intrusion detection system for secure IoTs and V2G communication. Alexandria Engineering Journal, 125, 424–440.
Qiu, X., Shi, L., & Fan, P. (2025). A cooperative intrusion detection system for internet of things using fuzzy logic and ensemble of convolutional neural networks. Scientific Reports, 15, 15934. https://doi.org/10.1038/s41598-025-99938-1
Karakaya, A. (2025). A hybrid approach for IoT security: Combining ensemble learning with fuzzy logic. Sensors, 25(18), 5668. https://doi.org/10.3390/s25185668
Kostiuk, Y. V., Skladannyi, P. M., & Hnatchenko, D. D. (2026). Risk-adaptive authorization in Zero Trust with dynamic trust and tokens. Problems in Programming, 1, 66–81. https://doi.org/10.15407/pp2026.01.066
Hassan, M. M., Gumaei, A. H., Alsanad, A., Alrubaian, M., & Fortino, G. (2020). A hybrid deep learning model for efficient intrusion detection in big data environment. Information Sciences, 513, 386–396.
Kostiuk, Y., Rzaieva, S., & Rzaiev, D. (2026). Intelligent network traffic analysis for detecting information security incidents. Science and Technology Today, 2(56), 1909–1940. https://doi.org/10.52058/2786-6025-2026-2(56)-1909-1928
K, M., Renuka, S., K, L., & Y. M., M. (2025). Hybrid deep learning approach for efficient intrusion detection using DCNN and BiLSTM. In 2025 3rd International Conference on Data Science and Network Security (ICDSNS) (pp. 1–6). IEEE. https://doi.org/10.1109/ICDSNS65743.2025.11168612
Skladannyi, P., Kostiuk, Y., & Rzaieva, S. (2026). Continuous access assessment in Zero Trust Access Management based on security event signals and dynamic session management. Mathematical Machines and Systems, 1, 29–46. https://doi.org/10.34121/1028-9763-2026-1-29-46
Checker, S., Yadav, M., & Katarya, R. (2023). A survey on intrusion detection system for IoT networks based on artificial intelligence. In 2023 International Conference on Electrical, Electronics, Communication and Computers (ELEXCOM) (pp. 1–6). IEEE. https://doi.org/10.1109/ELEXCOM58812.2023.10370067
Rzaeva, S., Skladannyi, P., Kostiuk, Y., Abramov, V., & Kravchenko, V. (2025). Adaptive information security management in cloud-oriented intelligent transportation systems. Ukrainian Scientific Journal of Information Security, 31(1), 23–36. https://doi.org/10.18372/2225-5036.31.20634
Pawlik, L., Wilk-Jakubowski, J. L., Grabski, P. T., & Wilk-Jakubowski, G. (2025). Securing the electrified future: A systematic review of cyber attacks, intrusion and anomaly detection, and authentication in electric vehicle charging infrastructure. Energies, 18(18), 4847. https://doi.org/10.3390/en18184847
Skladannyi, P. M., Hulak, H. M., & Kostiuk, Y. V. (2025). Chaotic number generator with fuzzy control for cryptographic systems with dynamic trust. Telecommunication and Information Technologies, 4(89), 137–147. https://doi.org/10.31673/2412-4338.2025.048916
Kostiuk, Y., Skladannyi, P., Rzaieva, S., Samoilenko, Y., & Korshun, N. (2025). Intelligent control and protection systems in cyber-physical and cloud-based Smart Grid environments. Cybersecurity: Education, Science, Technique, 2(30), 125–156. https://doi.org/10.28925/2663-4023.2025.30.956
Kamboj, A., Ravindran, V., & Ojha, S. (2025). A comparative analysis of signature-based and anomaly-based intrusion detection systems. International Journal of Latest Technology in Engineering Management & Applied Science, 14, 209–214. https://doi.org/10.51583/IJLTEMAS.2025.140500026
Li, P., Wang, H., Tian, G., & Fan, Z. (2024). A cooperative intrusion detection system for the Internet of Things using convolutional neural networks and black hole optimization. Sensors, 24(15), 4766. https://doi.org/10.3390/s24154766
Kostiuk, Y., Skladannyi, P., Rzaieva, S., Mazur, N., Cherevyk, V., & Anosov, A. (2025). Features of network attack implementation through TCP/IP protocols. Cybersecurity: Education, Science, Technique.
Yang, G., Huang, Q., Lv, H., & Lu, X. (2025). A network intrusion detection system based on convolutional neural network. In 2025 IEEE International Conference on High Performance Computing and Communications (HPCC) (pp. 1265–1271).
Kostiuk, Y., Khorolska, K., Bebeshko, B., Dovzhenko, N., Korshun, N., & Pazynin, A. (2025). Tools for ensuring information security against hidden threats in cloud computing infrastructure. Cybersecurity: Education, Science, Technique, 4(28), 633–655. https://doi.org/10.28925/2663-4023.2025.28.857
Zhang, L., & Xu, C. (2022). A intrusion detection model based on convolutional neural network and feature selection. In 2022 5th International Conference on Artificial Intelligence and Big Data (ICAIBD) (pp. 162–167). IEEE. https://doi.org/10.1109/ICAIBD55127.2022.9820384
Skladannyi, P., Kostiuk, Y., Rzaieva, S., Samoilenko, Y., & Savchenko, T. (2025). Development of modular neural networks for detecting various classes of network attacks. Cybersecurity: Education, Science, Technique, 3(27), 534–548. https://doi.org/10.28925/2663-4023.2025.27.772
Farhan, S., Mubashir, J., Haq, Y. U., et al. (2025). Enhancing network security: An intrusion detection system using residual network-based convolutional neural network. Cluster Computing, 28, 251. https://doi.org/10.1007/s10586-025-05156-9
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Юлія Костюк, Павло Складанний
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
