DOI:
https://doi.org/10.64539/sjcs.v2i1.2026.404Keywords:
Intrusion Detection, Convolutional Neural Networks, Deep Learning, Cybersecurity, UNSW-NB15Abstract
The rapid expansion of cloud computing, Internet of Things (IoT), and distributed network environments has significantly increased vulnerability to sophisticated cyber threats, exposing the limitations of traditional signature-based intrusion detection systems. Although deep learning techniques, particularly Convolutional Neural Networks (CNNs), have shown promising performance in intrusion detection, challenges related to validation transparency, statistical reliability, and interpretability remain inadequately addressed. This study proposes an intelligent CNN-based intrusion detection framework designed to improve detection accuracy, robustness, and model explainability. The framework is evaluated using the UNSW-NB15 benchmark dataset, which reflects realistic modern cyber-attack scenarios. A comprehensive preprocessing pipeline involving data cleaning, categorical encoding, feature normalization, and data reshaping is applied to enhance learning efficiency. To ensure unbiased evaluation, stratified k-fold cross-validation and an independent held-out test set are employed. Experimental results demonstrate that the proposed CNN achieves a test accuracy of 91.8%, with balanced precision, recall, and F1-score across benign and malicious traffic classes. Multi-class detection analysis further confirms the model’s capability to distinguish among diverse attack categories. Statistical validation using mean performance metrics, standard deviation, and confidence intervals demonstrates stable generalization performance. Additionally, Gradient-weighted Class Activation Mapping (Grad-CAM) is used to enhance interpretability by identifying network-level features that influence classification decisions. An ablation study further validates the effectiveness of key architectural components. The results indicate that the proposed framework provides a reliable, scalable, and interpretable solution for intelligent intrusion detection in modern high-dimensional network environments.
References
[1] A. Anandita Iyer and K. S. Umadevi, “Role of AI and Its Impact on the Development of Cyber Security Applications,” Artificial Intelligence and Cyber Security in Industry 4.0, 2023, pp. 23–46. https://doi.org/10.1007/978-981-99-2115-7_2.
[2] M. Sarhan, S. Layeghy, N. Moustafa, and M. Portmann, “NetFlow Datasets for Machine Learning-Based Network Intrusion Detection Systems,” Big Data Technologies and Applica-tions, 2021, pp. 117–135. https://doi.org/10.1007/978-3-030-72802-1_9.
[3] G. P. Oise, S. A. Oyedotun, O. C. Nwabuokei, A. E. Babalola, and N. B. Unuigbokhai, “En-hanced Prediction of Coronary Artery Disease Using Logistic Regression,” Fudma Journal of Sciences, vol. 9, no. 3, pp. 201–208, Mar. 2025, https://doi.org/10.33003/fjs-2025-0903-3263.
[4] N. B. Unuigbokhai, G. P. Oise, B. E. Akilo, O. C. Nwabuokei, J. A. Odimayomi, S. K. Bakare, O. M. Atake, “Advancements in Federated Learning for Secure Data Sharing in Financial Services,” Fudma Journal of Sciences, vol. 9, no. 5, pp. 80–86, May 2025, https://doi.org/10.33003/fjs-2025-0905-3207.
[5] A. M. K. Adawadkar and N. Kulkarni, “Cyber-security and reinforcement learning — A brief survey,” Eng Appl Artif Intell, vol. 114, p. 105116, Sep. 2022, https://doi.org/10.1016/j.engappai.2022.105116.
[6] G. Oise and S. Konyeha, “E-Waste Management Through Deep Learning: A Sequential Neural Network Approach,” Fudma Journal of Sciences, vol. 8, no. 3, pp. 17–24, Jul. 2024, https://doi.org/10.33003/fjs-2024-0804-2579.
[7] S. Dasgupta, A. Piplai, P. Ranade, and A. Joshi, “Cybersecurity Knowledge Graph Im-provement with Graph Neural Networks,” in 2021 IEEE International Conference on Big Data (Big Data), IEEE, Dec. 2021, pp. 3290–3297. https://doi.org/10.1109/BigData52589.2021.9672062.
[8] T. Bilot, N. El Madhoun, K. Al Agha, and A. Zouaoui, “Graph Neural Networks for Intru-sion Detection: A Survey,” IEEE Access, vol. 11, pp. 49114–49139, 2023, https://doi.org/10.1109/ACCESS.2023.3275789.
[9] B. Lakha, S. L. Mount, E. Serra, and A. Cuzzocrea, “Anomaly Detection in Cybersecurity Events Through Graph Neural Network and Transformer-Based Model: A Case Study with BETH Dataset,” in 2022 IEEE International Conference on Big Data (Big Data), IEEE, Dec. 2022, pp. 5756–5764. https://doi.org/10.1109/BigData55660.2022.10020336.
[10] A. Shruti and Sreekumar, “Fintech and Financial Inclusion—A Review of Risk Manage-ment Strategies,” International Program and Project Management — Best Practices in Select-ed Industries, 2025, pp. 199–216. https://doi.org/10.1007/978-3-031-80275-1_9.
[11] R. W. Idayani, R. Nadlifatin, A. P. Subriadi, and Ma. J. J. Gumasing, “A Comprehensive Re-view on How Cyber Risk Will Affect the Use of Fintech,” Procedia Comput Sci, vol. 234, pp. 1356–1363, 2024, https://doi.org/10.1016/j.procs.2024.03.134.
[12] R. Gadge, A. Masharkar, A. Singh, N. Shelke, and A. Pimpalkar, “Managing Cybersecurity Risks in Emerging Technologies: Challenges and Solutions,” in 2024 International Confer-ence on Artificial Intelligence and Quantum Computation-Based Sensor Application (ICAI-QSA), IEEE, Dec. 2024, pp. 1–9. https://doi.org/10.1109/ICAIQSA64000.2024.10882358.
[13] S. AlBenJasim, H. Takruri, R. Al-Zaidi, and T. Dargahi, “Development of cybersecurity framework for FinTech innovations: Bahrain as a case study,” International Cybersecurity Law Review, vol. 5, no. 4, pp. 501–532, Dec. 2024, https://doi.org/10.1365/s43439-024-00130-4.
[14] M. Radha, Y. Vasa, A. R. Kumbham, P. Vallurupalli, S. A. Kumar, and D. A, “A Hybrid Graph Neural Network-Based Reinforcement Learning Approach for Adaptive Cybersecu-rity Risk Management in FinTech,” in 2025 International Conference on Computing Technol-ogies & Data Communication (ICCTDC), IEEE, Jul. 2025, pp. 1–6. https://doi.org/10.1109/ICCTDC64446.2025.11158732.
[15] J. Alom, M. S. Ullah, M. T. Islam, M. Niloy, R. Islam, and S. Firdaus, “Adaptive Multi-Agent Reinforcement Learning for Intrusion Mitigation Aligned with Smart City,” in 2025 International Conference on Quantum Photonics, Artificial Intelligence, and Networking (QPAIN), IEEE, Jul. 2025, pp. 1–6. https://doi.org/10.1109/QPAIN66474.2025.11172093.
[16] G. Oise and S. Konyeha, “Environmental impacts in e-waste management using deep learn-ing,” Discover Artificial Intelligence, vol. 5, no. 1, p. 210, Aug. 2025, https://doi.org/10.1007/s44163-025-00376-9.
[17] S. A. Oyedotun, G. P. Oise, and C. E. Ozobialu, “Towards Intelligent Cybersecurity in SCADA and DCS Environments: Anomaly Detection Using Multimodal Deep Learning and Explainable AI,” Journal of Science Research and Reviews, vol. 2, no. 3, pp. 20–31, Jul. 2025, https://doi.org/10.70882/josrar.2025.v2i3.76.
[18] S. A. Oyedotun, O. P. Ejenarhome, and G. P. Oise, “Learning Analytics and Predictive Mod-eling: Enhancing Student Success through Data-Driven Insights,” Journal of Science Re-search and Reviews, vol. 2, no. 3, pp. 42–51, Jul. 2025, https://doi.org/10.70882/josrar.2025.v2i3.77.
[19] D. Azamuke, M. Katarahweire, and E. Bainomugisha, “Financial Fraud Detection Using Rich Mobile Money Transaction Datasets,” Towards new e-Infrastructure and e-Services for Developing Countries, 2025, pp. 190–208. https://doi.org/10.1007/978-3-031-81573-7_16.
[20] A. Uprety and D. B. Rawat, “Reinforcement Learning for IoT Security: A Comprehensive Survey,” IEEE Internet Things J, vol. 8, no. 11, pp. 8693–8706, Jun. 2021, https://doi.org/10.1109/JIOT.2020.3040957.
[21] T. T. Nguyen and V. J. Reddi, “Deep Reinforcement Learning for Cyber Security,” IEEE Trans Neural Netw Learn Syst, vol. 34, no. 8, pp. 3779–3795, Aug. 2023, https://doi.org/10.1109/TNNLS.2021.3121870.
[22] S. Munikoti, D. Agarwal, L. Das, M. Halappanavar, and B. Natarajan, “Challenges and Opportunities in Deep Reinforcement Learning With Graph Neural Networks: A Compre-hensive Review of Algorithms and Applications,” IEEE Trans Neural Netw Learn Syst, vol. 35, no. 11, pp. 15051–15071, Nov. 2024, https://doi.org/10.1109/TNNLS.2023.3283523.
[23] M. Pham, V. Vaze, and P. Chin, “Strategic Cyber Defense via Reinforcement Learning-Guided Combinatorial Auctions,” in 2025 IEEE High Performance Extreme Computing Con-ference (HPEC), IEEE, Sep. 2025, pp. 1–7. https://doi.org/10.1109/HPEC67600.2025.11196565.
[24] S. A. Oyedotun, G. P. Oise, B. E. Akilo, O. C. Nwabuokei, P. O. Ejenarhome, M. Fole, C. J. Onwuzo, “The Role of Internal Audit in Fraud Detection and Prevention: A Multi-Contextual Review and Research Agenda,” Journal of Science Research and Reviews, vol. 2, no. 2, pp. 76–85, May 2025, https://doi.org/10.70882/josrar.2025.v2i2.51.
[25] G. P. Oise, C. J. Onwuzo, M. Fole, S. A. Oyedotun, J. A. Odimayomi,N. B. Unuigbokhai, P. O. Ejenarhome, B. E. Akilo, “Decentralized Deep Learning in Healthcare: Addressing Data Privacy with Federated Learning,” Fudma Journal of Sciences, vol. 9, no. 6, pp. 19–26, Jun. 2025, https://doi.org/10.33003/fjs-2025-0906-3714.
[26] B. Blakely, “An Experimental Platform for Autonomous Intelligent Cyber-Defense Agents: Towards a collaborative community approach (WIPP),” in 2022 Resilience Week (RWS), IEEE, Sep. 2022, pp. 1–7. https://doi.org/10.1109/RWS55399.2022.9984037.
[27] G. Oise, Cyprian C. Konyeha, O. T. Comfort, S. Konyeha, and C. O. Emmanueld, “The Inte-gration of Internet of Things (IoT) in Smart Classrooms: Opportunities, Challenges, and Fu-ture Trajectories,” Journal of Digital Learning And Distance Education, vol. 4, no. 3, pp. 1554–1567, Aug. 2025, https://doi.org/10.56778/jdlde.v4i3.537.
[28] G. G. James, G. P. Oise, E. G. Chukwu, N. A. Michael, W. F. Ekpo, and P. E. Okafor, “Opti-mizing Business Intelligence System Using Big Data and Machine Learning,” Journal of In-formation Systems and Informatics, vol. 6, no. 2, pp. 1215–1236, Jun. 2024, https://doi.org/10.51519/journalisi.v6i2.631.
