An Intelligent Cybersecurity Architecture for Network Log-Based Intrusion Detection Employing a Hybrid Machine Learning Approach
Keywords:
Intrusion Detection System, Network Logs, Hybrid Machine Learning, Cybersecurity ArchitectureAbstract
The increasing sophistication of cyberattacks has significantly challenged traditional intrusion detection systems (IDS), particularly in environments generating large-scale network logs. This study proposes an intelligent cybersecurity architecture for network log-based intrusion detection using a hybrid machine learning approach that integrates statistical learning and deep feature representation techniques. The objective is to enhance detection accuracy, reduce false positives, and improve adaptability to evolving malicious traffic patterns. The proposed architecture leverages multi-stage preprocessing, feature engineering, and ensemble-based classification mechanisms inspired by recent advancements in deep neural networks and hybrid IDS models (Gao et al., 2020; Bendiab et al., 2020).
The framework integrates both supervised and unsupervised learning paradigms to address labeled and unlabeled log data scenarios. Additionally, it incorporates insights from prior studies on IoT, SCADA, and encrypted traffic detection, emphasizing robustness across heterogeneous network environments (De Lucia & Cotton, 2019; Xin et al., 2022). Experimental design considerations are aligned with machine learning evaluation standards in cybersecurity domains (Rajesh & Satyanarayana, 2021).
The results indicate that hybridization of classical machine learning with deep learning feature extractors significantly improves detection efficiency, particularly in high-dimensional log environments. The architecture demonstrates scalability, interpretability, and adaptability for modern enterprise networks. This study contributes a unified and extensible IDS framework suitable for real-time deployment in cloud, IoT, and enterprise infrastructures
Downloads
References
1. Abdulhammed R, Faezipour M, Abuzneid A, AbuMallouh A. Deep and machine learning approaches for anomaly-based intrusion detection of imbalanced network traffic. IEEE Sens Lett. 2018;3(1):1–4.
2. Alshammari A, Aldribi A. Apply machine learning techniques to detect malicious network traffic in cloud computing. J Big Data. 2021;8(1):1–24.
3. Bendiab G, Shiaeles S, Alruban A, Kolokotronis N. IoT malware network traffic classification using visual representation and deep learning. 2020 6th IEEE Conference on Network Softwarization (NetSoft), pp. 444–9, IEEE, Jun 2020.
4. De Lucia MJ, Cotton C. Detection of encrypted malicious network traffic using machine learning. MILCOM 2019-2019 IEEE Military Communications Conference (MILCOM), pp. 1–6, IEEE, Nov 2019.
5. Feng J, Shen L, Chen Z, Wang Y, Li H. A two-layer deep learning method for android malware detection using network traffic. IEEE Access. 2020;8:125786–96.
6. Gao M, Ma L, Liu H, Zhang Z, Ning Z, Xu J. Malicious networktraffic detection based on deep neural networks and associationanalysis.Sensors. 2020;20(5):1452.
7. Ge M, Fu X, Syed N, Baig Z, Teo G, Robles-Kelly A. Deeplearning-based intrusion detection for IoT networks. 2019 IEEE24th Pacific Rim International Symposium on Dependable Comput-ing (PRDC), pp. 256–25609, IEEE, Dec 2019.
8. Hwang RH, Peng MC, Huang CW, Lin PC, Nguyen VL. An unsupervised deep learning model for early network traffic anomaly detection. IEEE Access. 2020;8:30387–99.
9. Indrasiri PL, Lee E, Rupapara V, Rustam F, Ashraf I. Malicious traffic detection in iot and local networks using stacked ensemble classifier. Comput Mater Contin. 2022;71(1):489–515.
10. Mitsuhashi R, Satoh A, Jin Y, Iida K, Shinagawa T, Takai Y. Identifying malicious dns tunnel tools from doh traffic using hierarchical machine learning classification. Information Security: 24th International Conference, ISC 2021, Virtual Event, November 10–12, 2021, Proceedings 24, pp. 238–56, Springer International Publishing, 2021.
11. Rajesh L, Satyanarayana P. Evaluation of machine learning algorithms for detection of malicious traffic in scada network. J Electr Eng Technol. 2021;1–16.
12. Rose JR, Swann M, Bendiab G, Shiaeles S, Kolokotronis N. Intrusion detection using network traffic profiling and machine learning for IoT. 2021 IEEE 7th International Conference on Network Softwarization (NetSoft), pp. 409–15, IEEE, Jun 2021.
13. Shafiq M, Tian Z, Bashir AK, Du X, Guizani M. CorrAUC: a malicious bot-IoT traffic detection method in IoT network using machine-learning techniques. IEEE Internet Things J. 2020;8(5):3242–54.
14. Wang W, Zhu M, Zeng X, Ye X, Sheng Y. Malware traffic classification using convolutional neural network for representation learning. 2017 International Conference on Information Networking (ICOIN), pp. 712–7, IEEE, Jan 2017.
15. Xin L, Ziang L, Yingli Z, Wenqiang Z, Dong L, Qingguo Z. TCN enhanced novel malicious traffic detection for IoT devices. ConnSci. 2022;34(1):1322–41.
16. Zheng J, Zeng Z, Feng T. GCN-ETA: high-efficiency encrypted malicious traffic detection. Secur Commun Netw. 2022;2022:1–11.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Dr. Tatsuya Endo, Dr. Honoka Sato (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles published by The Parthenon Frontiers and its associated journals are distributed under the terms of the Creative Commons Attribution (CC BY 4.0) International License unless otherwise stated.
Authors retain full copyright of their published work. By submitting their manuscript, authors agree to grant The Parthenon Frontiers a non-exclusive license to publish, archive, and distribute the article worldwide. Authors are free to:
-
Share their article on personal websites, institutional repositories, or social media platforms.
-
Reuse their content in future works, presentations, or educational materials, provided proper citation of the original publication.
