A Novel Ensemble of Deep Learning Approach for Cybersecurity Intrusion Detection with Explainable Artificial Intelligence
Source abstract
Abstract
In today’s increasingly interconnected digital world, cyber threats have grown in frequency and sophistication, making intrusion detection systems a critical component of modern cybersecurity frameworks. Traditional IDS methods, often based on static signatures and rule-based systems, are no longer sufficient to detect and respond to complex and evolving attacks. To address these challenges, Artificial Intelligence and machine learning have emerged as powerful tools for enhancing the accuracy, adaptability, and automation of IDS solutions. This study presents a novel, hybrid ensemble learning-based intrusion detection framework that integrates deep learning and traditional ML algorithms with explainable artificial intelligence for real-time cybersecurity applications. The proposed model combines an Artificial Neural Network and Support Vector Machine as base classifiers and employs a Random Forest as a meta-classifier to fuse predictions, improving detection performance. Recursive Feature Elimination is utilized for optimal feature selection, while SHapley Additive exPlanations (SHAP) provide both global and local interpretability of the model’s decisions. The framework is deployed using a Flask-based web interface in the Amazon Elastic Compute Cloud environment, capturing live network traffic and offering sub-second inference with visual alerts. Experimental evaluations using the NSL-KDD dataset demonstrate that the ensemble model outperforms individual classifiers, achieving a high accuracy of 99.40%, along with excellent precision, recall, and F1-score metrics. This research not only enhances detection capabilities but also bridges the trust gap in AI-powered security systems through transparency. The solution shows strong potential for application in critical domains such as finance, healthcare, industrial IoT, and government networks, where real-time and interpretable threat detection is vital.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Network Security and Intrusion Detection · Anomaly Detection Techniques and Applications · Advanced Malware Detection Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Cybersecurity, College of Computer, Qassim University, Buraydah 52571, Saudi Arabia
Funding
Qassim University
References (38)
Show source-provided references
1. Perez, S.I., and Criado, R. (2022). Increasing the Effectiveness of Network Intrusion Detection Systems (NIDSs) by Using Multiplex Networks and Visibility Graphs. Mathematics, 11.10.3390/math11010107 ↗
2. (2025, May 23). 100+ Network Security Statistics in 2025. AIMultiple. Available online: https://research.aimultiple.com/network-security-statistics/.
3. (2025, May 23). Infographic: Cybercrime Expected to Skyrocket in Coming Years. Statista Daily Data. Available online: https://www.statista.com/chart/28878/expected-cost-of-cybercrime-until-2027.
4. Mousavi, S.M., and St-Hilaire, M. (2015, January 16–19). Early detection of DDoS attacks against SDN controllers. Proceedings of the 2015 International Conference on Computing, Networking and Communications (ICNC), Garden Grove, CA, USA.10.1109/ICCNC.2015.7069319 ↗
5. Optimal feature selection with CNN-feature learning for DDoS attack detection using meta-heuristic-based LSTM10.1007/s41315-022-00224-4 ↗
6. Research on Network Traffic Anomaly Detection Method Based on Deep Learning10.1088/1742-6596/1861/1/012007 ↗
7. (2025, May 23). “2025 DDoS Attack Statistics: Alarming Prediction—VPNRanks Predicts 1 in 20 Internet Users Will Likely To Be Hit!”. Available online: https://www.vpnranks.com/resources/ddos-attack-statistics/.
8. (2025, May 24). “NSL-KDD|Datasets|Research|Canadian Institute for Cybersecurity|UNB.”. Available online: https://www.unb.ca/cic/datasets/nsl.html.
9. Apply machine learning techniques to detect malicious network traffic in cloud computing10.1186/s40537-021-00475-1 ↗
10. Network intrusion detection system: A systematic study of machine learning and deep learning approaches10.1002/ett.4150 ↗
11. The March of IDES: Early History of Intrusion-Detection Expert Systems
12. Dong, B., and Wang, X. (2016, January 4–6). Comparison deep learning method to traditional methods using for network intrusion detection. Proceedings of the 2016 8th IEEE International Conference on Communication Software and Networks (ICCSN), Beijing, China.10.1109/ICCSN.2016.7586590 ↗
13. New hybrid method for attack detection using combination of evolutionary algorithms, SVM, and ANN10.1016/j.comnet.2020.107168 ↗
14. Network anomaly detection research: A survey
15. Wattanapongsakorn, N., Srakaew, S., Wonghirunsombat, E., Sribavonmongkol, C., Junhom, T., Jongsubsook, P., and Charnsripinyo, C. (2012, January 25–27). A Practical Network-Based Intrusion Detection and Prevention System. Proceedings of the 2012 IEEE 11th International Conference on Trust, Security and Privacy in Computing and Communications, Liverpool, UK.10.1109/TrustCom.2012.46 ↗
16. Ahmed, M., and Haskell-Dowland, P. (2023). Cybersafe Capabilities and Utilities for Smart Cities. Cybersecurity for Smart Cities. Advanced Sciences and Technologies for Security Applications, Springer.10.1007/978-3-031-24946-4 ↗
17. Bakar, R.A., Huang, X., Javed, M.S., Hussain, S., and Majeed, M.F. (2023). An Intelligent Agent-Based Detection System for DDoS Attacks Using Automatic Feature Extraction and Selection. Sensors, 23.10.3390/s23063333 ↗
18. Masum, M., Shahriar, H., Haddad, H., Faruk, J.H., Valero, M., Khan, A., Rahman, M.A., Adnan, M.I., Cuzzocrea, A., and Wu, F. (2021, January 15–18). Bayesian Hyperparameter Optimization for Deep Neural Network-Based Network Intrusion Detection. Proceedings of the 2021 IEEE International Conference on Big Data (Big Data), Orlando, FL, USA.10.1109/BigData52589.2021.9671576 ↗
19. A novel ensemble learning-based model for network intrusion detection10.1007/s40747-023-01013-7 ↗
20. A Novel Ensemble Framework for an Intelligent Intrusion Detection System10.1109/ACCESS.2021.3116219 ↗
21. Verma, P., Dumka, A., Singh, R., Ashok, A., Gehlot, A., Malik, P.K., Gaba, G.S., and Hedabou, M. (2021). A Novel Intrusion Detection Approach Using Machine Learning Ensemble for IoT Environments. Appl. Sci., 11.10.3390/app112110268 ↗
22. Ensemble classification for intrusion detection via feature extraction based on deep Learning10.1007/s00500-021-06067-8 ↗
23. An Explainable Ensemble Deep Learning Approach for Intrusion Detection in Industrial Internet of Things10.1109/ACCESS.2023.3323573 ↗
24. Divakar, S., Priyadarshini, R., and Mishra, B.K. (2020, January 26–27). A Robust Intrusion Detection System using Ensemble Machine Learning. Proceedings of the 2020 IEEE International Women in Engineering (WIE) Conference on Electrical and Computer Engineering (WIECON-ECE), Bhubaneswar, India.10.1109/WIECON-ECE52138.2020.9397969 ↗
25. An Ensemble Learning Based Intrusion Detection Model for Industrial IoT Security10.26599/BDMA.2022.9020032 ↗
26. Attack Classification of Imbalanced Intrusion Data for IoT Network Using Ensemble-Learning-Based Deep Neural Network10.1109/JIOT.2023.3244810 ↗
27. Thilakarathne, N.N., Bakar, M.S.A., Abas, P.E., and Yassin, H. (2025). A novel cyber threat intelligence platform for evaluating the risk associated with smart agriculture. Sci. Rep., 15.10.1038/s41598-025-85320-8 ↗
28. Kalaivani, D. (2022). An Intrusion Detection System Based on Data Analytics and Convolutional Neural Network in NSS-KDD dataset. Machine Learning Algorithms for Intelligent Data Analytics, Technoarete Research and Development Association.
29. Yedukondalu, G., Bindu, G.H., Pavan, J., Venkatesh, G., and SaiTeja, A. (2021, January 2–4). Intrusion Detection System Framework Using Machine Learning. Proceedings of the 2021 Third International Conference on Inventive Research in Computing Applications (ICIRCA), Coimbatore, India.10.1109/ICIRCA51532.2021.9544717 ↗
30. Alabdulatif, A., and Thilakarathne, N.N. (2024). A Novel Cloud-Enabled Cyber Threat Hunting Platform for Evaluating the Cyber Risks Associated with Smart Health Ecosystems. Appl. Sci., 14.10.3390/app14209567 ↗
31. Nwakanma, C.I., Ahakonye, L.A.C., Njoku, J.N., Odirichukwu, J.C., Okolie, S.A., Uzondu, C., Nweke, C.C.N., and Kim, D.-S. (2023). Explainable Artificial Intelligence (XAI) for Intrusion Detection and Mitigation in Intelligent Connected Vehicles: A Review. Appl. Sci., 13.10.3390/app13031252 ↗
32. Explainable Artificial Intelligence (XAI) to Enhance Trust Management in Intrusion Detection Systems Using Decision Tree Model10.1155/2021/6634811 ↗
33. XAI for intrusion detection system: Comparing explanations based on global and local scope10.1007/s11416-022-00441-2 ↗
34. AI-IDS: Application of Deep Learning to Real-Time Web Intrusion Detection10.1109/ACCESS.2020.2986882 ↗
35. Viharika, S., and Balaji, N. (2024, January 12–13). AI-Driven Intrusion Detection Systems in Cloud Infrastructures: A Comprehensive Review of Hybrid Security Models and Future Directions. Proceedings of the 2024 4th International Conference on Ubiquitous Computing and Intelligent Information Systems (ICUIS), Gobichettipalayam, India.10.1109/ICUIS64676.2024.10866856 ↗
36. Andronikidis, G., Eleftheriadis, C., Batzos, Z., Kyranou, K., Maropoulos, N., Sargsyan, G., Grammatikis, P.R., and Sarigiannidis, P. (2024, January 2–4). AI-Driven Anomaly and Intrusion Detection in Energy Systems: Current Trends and Future Direction. Proceedings of the 2024 IEEE International Conference on Cyber Security and Resilience (CSR), London, UK.10.1109/CSR61664.2024.10679380 ↗
37. Intelligent parameter-based in-network IDS for IoT using UNSW-NB15 and BoT-IoT datasets10.1016/j.jfranklin.2024.107440 ↗
38. Ali, M., Pervez, S., Hosseini, S.E., and Siddhu, M.K. (2025, June 28). Evaluation and Detection of Cyberattack in IoT-Based Smart City Networks Using Machine Learning on the UNSW-NB15 Dataset.|EBSCOhost. Available online: https://openurl.ebsco.com/contentitem/doi:10.3991%2Fijoe.v21i02.52671?sid=ebsco:plink:crawler&id=ebsco:doi:10.3991%2Fijoe.v21i02.52671.