Hybrid Deep Learning and Fuzzy Logic Intrusion Detection Model for Modern Telecommunication Networks
DOI:
https://doi.org/10.70062/jeci.v1i3.225Keywords:
Convolutional Neural Networks, Cybersecurity, Fuzzy Logic, Intrusion Detection, Telecommunication NetworksAbstract
The increasing sophistication of cyberattacks has made traditional security systems less effective, particularly in the context of modern telecommunication networks. These evolving threats require more advanced, adaptive intrusion detection systems (IDS) to provide reliable protection. This study proposes a Hybrid IDS Model that combines deep learning, specifically Convolutional Neural Networks (CNN), with fuzzy logic to enhance detection accuracy and adaptability. The objective of this research is to develop an intelligent system capable of detecting both known and unknown cyber threats by leveraging the strengths of CNNs for feature extraction and fuzzy logic for handling imprecision in network data. The hybrid model introduces CNN to automatically extract critical features from network traffic, enabling the system to learn complex attack patterns. The fuzzy logic component processes the CNN outputs by applying fuzzy rules to classify network behavior as normal or anomalous, thus addressing the uncertainty inherent in network data. The model achieves 93% detection accuracy, outperforming traditional signature-based IDS systems, which are less effective at detecting zero-day and evolving threats. The proposed IDS is also evaluated for real-time applicability, showing strong performance in large-scale telecommunication networks. This study’s findings emphasize the system’s ability to adapt to new and evolving attacks, providing a more robust and scalable solution compared to conventional IDS. The research highlights the effectiveness of combining deep learning with fuzzy logic in cybersecurity, offering promising results for the future of telecommunication network protection. Future work will explore integrating advanced fuzzy systems and experimenting with other deep learning techniques to further enhance detection capabilities in the face of ever-evolving threats.
References
Adinarayana, T., Umamaheswararao, S., Sri, R. S., Ponnapalli, S., & Dornala, R. R. (2024). Enhancing cyber-physical system security: A novel approach to real-time cyber attack detection and mitigation. In Proceedings of the 8th International Conference on Electronics, Communication and Aerospace Technology (ICECA 2024) (pp. 592–598). https://doi.org/10.1109/ICECA63461.2024.10800946
Agubor, C. K., Chukwudebe, G. A., & Nosiri, O. C. (2015). Security challenges to telecommunication networks: An overview of threats and preventive strategies. Proceedings of the International Conference on Cyberspace Governance (CYBER-Abuja), 124–129. https://doi.org/10.1109/CYBER-Abuja.2015.7360500
Alsaadi, H. I. H., ALmuttari, R. M., Ucan, O. N., & Bayat, O. (2022). An adapting soft computing model for intrusion detection system. Computational Intelligence, 38(3), 855–875. https://doi.org/10.1111/coin.12433
Azhagiri, M., & Rajesh, A. (2016). A concept for minimizing false alarms and security compromise by coupled dynamic learning of system with fuzzy logics. Indian Journal of Science and Technology, 9(37), 90284. https://doi.org/10.17485/ijst/2016/v9i37/90284
Ben Atitallah, S., Driss, M., Boulila, W., & Koubaa, A. (2025). Securing industrial IoT environments: A fuzzy graph attention network for robust intrusion detection. IEEE Open Journal of the Computer Society, 6, 1065–1076. https://doi.org/10.1109/OJCS.2025.3587486
Birleanu, F. G., Anghelescu, P., & Bizon, N. (2019). Malicious and deliberate attacks and power system resiliency. In Power Systems (pp. 223–246). https://doi.org/10.1007/978-3-319-94442-5_9
d’Ambrosio, N., Lista, C., Perrone, G., & Romano, S. P. (2025). SMASH: An SDN-MTD framework for efficient honeypot deployment and insider threat mitigation. Computer Networks, 269, 111327. https://doi.org/10.1016/j.comnet.2025.111327
Hemalatha, S., Mahalakshmi, M., Vignesh, V., Geethalakshmi, M., Balasubramanian, D., & Jose, A. A. (2023). Deep learning approaches for intrusion detection with emerging cybersecurity challenges. In ICSCNA 2023 - Proceedings (pp. 1522–1529). https://doi.org/10.1109/ICSCNA58489.2023.10370556
Hnamte, V., & Hussain, J. (2023). Dependable intrusion detection system using deep convolutional neural network: A novel framework and performance evaluation approach. Telematics and Informatics Reports, 11, 100077. https://doi.org/10.1016/j.teler.2023.100077
Iantorno, M. S., & Beladda, K. (2025). Fuzzy logic for cybersecurity: Intrusion detection and privacy preservation with synthetic data. International Conference on Agents and Artificial Intelligence, 3, 376–382. https://doi.org/10.5220/0013137300003890
Imamguluyev, R. (2025). Detection and prevention of cyber attacks based on fuzzy logic and deep learning. In Lecture Notes in Networks and Systems (Vol. 1529, pp. 402–409). https://doi.org/10.1007/978-3-031-97992-7_45
Janati, M., & Messaoudi, F. (2025). Intrusion detection system-based network behavior analysis: A systemic literature review. International Journal of Advanced Computer Science and Applications, 16(3), 793–802. https://doi.org/10.14569/IJACSA.2025.0160378
Kalaiselvi, B., Kathiravan, P., Kaviyarasan, V., Sabarinathan, E., & Sudharsan, S. (2025). IoT-based network intruder detection and cyber attack prediction system. In Proceedings of the 8th International Conference on Computing Methodologies and Communication (ICCMC 2025) (pp. 206–211). https://doi.org/10.1109/ICCMC65190.2025.11140691
Kothari, S., Santhanam, G. R., Awadhutkar, P., Holland, B., Mathews, J., & Tamrawi, A. (2018). Catastrophic cyber-physical malware. In Advances in Information Security (Vol. 72, pp. 201–255). https://doi.org/10.1007/978-3-319-97643-3_7
Le, T. (2015). A recommended framework for anomaly intrusion detection system (IDS). Lecture Notes in Informatics (LNI), 246, 1829–1840.
Mithileash, A., Samuel, W. J., & Rajkumar, K. (2025). Integrating convolutional neural networks for enhanced real-time intrusion detection and automated attack classification. In 2025 International Conference on Data Science, Agents and Artificial Intelligence (ICDSAAI 2025). https://doi.org/10.1109/ICDSAAI65575.2025.11011737
Naaj, F. A., Himeur, Y., Mansoor, W., & Atalla, S. (2024). Intrusion detection using time-series imaging and transfer learning in smart grid environments. In Lecture Notes in Networks and Systems (Vol. 906, pp. 585–595). https://doi.org/10.1007/978-3-031-53824-7_52
Padmaja, R., & Challagundla, P. R. (2024). Exploring a two-phase deep learning framework for network intrusion detection. In SCEECS 2024. https://doi.org/10.1109/SCEECS61402.2024.10482198
Revathy, S., & Priya, S. S. (2023). Enhancing the efficiency of attack detection system using feature selection and feature discretization methods. International Journal on Recent and Innovation Trends in Computing and Communication, 11, 156–160. https://doi.org/10.17762/ijritcc.v11i4s.6322
Ryu, D., Lee, S., Yang, S., Jeong, J., Lee, Y., & Shin, D. (2024). Enhancing cybersecurity in energy IT infrastructure through a layered defense approach to major malware threats. Applied Sciences (Switzerland), 14(22), 10342. https://doi.org/10.3390/app142210342
Sharma, A. (2024). Designing intelligent IDS using deep learning and fuzzy logic for modern networks. International Journal of Cybersecurity and Networks, 7, 112–125. https://doi.org/10.1109/IJCNS.2024.10307813
Sharma, A., Kumar, V. G. K., & Poojari, A. (2025). Prioritize threat alerts based on false positives qualifiers provided by multiple AI models using evolutionary computation and reinforcement learning. Journal of The Institution of Engineers (India): Series B, 106(4), 1305–1322. https://doi.org/10.1007/s40031-024-01175-z
Sharma, J., Sonia, S., Kumar, K., Boulouard, Z., Aderemi, A. P., & Iwendi, C. (2025). Utilizing adaptive neuro-fuzzy inference systems (ANFIS) for intrusion detection systems. In Lecture Notes in Networks and Systems (Vol. 1312, pp. 11–23). https://doi.org/10.1007/978-3-031-94620-2_2
Singh, L., & Jahankhani, H. (2021). An approach of applying, adapting machine learning into the IDS and IPS component to improve its effectiveness and its efficiency. In Advanced Sciences and Technologies for Security Applications (pp. 43–71). https://doi.org/10.1007/978-3-030-88040-8_2
Somayajula, R., Raghavan, P., Chippagiri, S., & Ravula, P. (2025). Adaptive fuzzy-neural architectures for explainable intrusion detection in big data environments. In 2025 Global Conference in Emerging Technology (GINOTECH 2025). https://doi.org/10.1109/GINOTECH63460.2025.11076771
Sri, S. B., Reddy, A. R., Likhith, P., & Jabbar, M. A. (2023). Efficient intrusion detection system using convolutional long short term memory network. In Proceedings of the 7th IEEE International Conference on Computational Systems and Information Technology for Sustainable Solutions (CSITSS 2023). https://doi.org/10.1109/CSITSS60515.2023.10334106
Srinivasan, M., & Senthilkumar, N. C. (2025). Intrusion detection and prevention system (IDPS) model for IIoT environments using hybridized framework. IEEE Access, 13, 26608–26621. https://doi.org/10.1109/ACCESS.2025.3538461
Subramani, S., & Selvi, M. (2023). Intelligent IDS in wireless sensor networks using deep fuzzy convolutional neural network. Neural Computing and Applications, 35(20), 15201–15220. https://doi.org/10.1007/s00521-023-08511-2
Toliupa, S., et al. (2022). Building an intrusion detection system in critically important information networks with application of data mining methods. In Proceedings of the 16th International Conference on Advanced Trends in Radioelectronics, Telecommunications and Computer Engineering (TCSET 2022) (pp. 128–133). https://doi.org/10.1109/TCSET55632.2022.9767029
Tripathi, A., Upadhyay, P., & Goel, P. K. (2025). Industrial control systems (ICS) security: AI-based threat detection and prevention. In AI-Enhanced Cybersecurity for Industrial Automation (pp. 149–172). https://doi.org/10.4018/979-8-3373-3241-3.ch008
Wasnik, P., & Chavhan, N. (2023). Designing intelligent intrusion detection system using deep learning. In Proceedings of the 14th International Conference on Computing Communication and Networking Technologies (ICCCNT 2023). https://doi.org/10.1109/ICCCNT56998.2023.10307813
Xie, B., Xu, M., Jin, C., Cui, F., Li, Z., & Fan, H. (2024). HDCBAN: Hybrid neural network for network intrusion detection system. In 2024 9th International Conference on Computer and Communication Systems (ICCCS 2024) (pp. 427–434). https://doi.org/10.1109/ICCCS61882.2024.10603260
