Graph Neural Network-Based Approach for Anomaly Detection in Large-Scale Computer Networks
Keywords:
Graph Neural Networks, Anomaly Detection, Cybersecurity, Deep Learning, Network Traffic Analysis, Intrusion Detection SystemsAbstract
Large-scale computer networks generate massive volumes of traffic data, making anomaly detection a critical challenge for cybersecurity and network management. Traditional machine learning techniques often fail to capture complex relationships among network entities and dynamic traffic patterns. This study proposes a Graph Neural Network (GNN)-based anomaly detection framework that models network devices and communication links as graph structures. The proposed approach leverages node and edge features to learn hidden representations of network behavior and identify abnormal activities such as Distributed Denial-of-Service (DDoS) attacks, botnet communications, and insider threats. Experimental evaluation on benchmark network datasets demonstrates that the proposed GNN model achieves superior detection accuracy, precision, recall, and F1-score compared with conventional machine learning methods. The results indicate that graph-based deep learning techniques provide an effective solution for anomaly detection in modern large-scale computer networks.
References
1. Ahmed, M., Chen, J., Akpaku, E., & Bux, A. (2026). MAGNN: Multi-scale adaptive graph neural networks with contrastive learning for malicious network traffic detection. Journal of Parallel and Distributed Computing, 211, 105240.
2. Ares-Robledo, F., Rifà-Pous, H., & Clarisó, R. (2026). Graph neural networks for anomaly detection: A systematic review of dynamic temporal approaches. Artificial Intelligence Review, 59(129), 1–45.
3. Caville, E., Lo, W. W., Layeghy, S., & Portmann, M. (2022). Anomal-E: A self-supervised network intrusion detection system based on graph neural networks. arXiv Preprint arXiv:2207.06819.
4. Chen, L., Mao, Y., Zhou, H., Zhang, B., Wang, Z., & Wu, J. (2023). MTS-GAT: Multivariate time series anomaly detection based on graph attention networks. International Journal of Sensor Networks, 43(1), 38–49.
5. Ding, C., Sun, S., & Zhao, J. (2023). MST-GAT: A multimodal spatial-temporal graph attention network for time series anomaly detection. Information Fusion, 89, 527–536.
6. Guan, S., Zhao, B., Dong, Z., Gao, M., & He, Z. (2022). GTAD: Graph and temporal neural network for multivariate time series anomaly detection. Entropy, 24(6), 759.
7. Guo, W., Qiu, H., Liu, Z., Zhu, J., & Wang, Q. (2022). GLD-Net: Deep learning to detect DDoS attacks via topological and traffic feature fusion. Computational Intelligence and Neuroscience, 2022, 4611331.
8. Guo, J., Tang, S., Li, J., Pan, K., & Wu, L. (2024). RustGraph: Robust anomaly detection in dynamic graphs by jointly learning structural-temporal dependency. IEEE Transactions on Knowledge and Data Engineering, 36(7), 3472–3485.
9. Guo, H., Zhou, Z., Zhao, D., & Gaaloul, W. (2024). EGNN: Energy-efficient anomaly detection for IoT multivariate time series data using graph neural networks. Future Generation Computer Systems, 151, 45–56.
10. Hassani, K., & Khasahmadi, A. H. (2020). Contrastive multi-view representation learning on graphs. Proceedings of the International Conference on Machine Learning, 4116–4126.
11. Jiang, L., Ryan, R., Li, Q., & Ferdosian, N. (2025). A survey of heterogeneous graph neural networks for cybersecurity anomaly detection. arXiv Preprint arXiv:2510.26307.
12. Khemani, B., Patil, S., Kotecha, K., & Tanwar, S. (2024). A review of graph neural networks: Concepts, architectures, techniques, challenges, datasets, applications, and future directions. Journal of Big Data, 11(18), 1–52.
13. King, I. J., & Huang, H. H. (2023). Euler: Detecting network lateral movement via scalable temporal link prediction. ACM Transactions on Privacy and Security, 26(4), 1–28.
14. Kim, H., Lee, B. S., Shin, W. Y., & Lim, S. (2022). Graph anomaly detection with graph neural networks: Current status and challenges. arXiv Preprint arXiv:2209.14930.
15. Kong, J., Wang, K., Jiang, M., & Tao, X. (2024). GMAD: Multivariate time series anomaly detection based on graph matching learning. Expert Systems with Applications, 245, 122822.
16. Latif-Martínez, H., Suárez-Varela, J., Cabellos-Aparicio, A., & Barlet-Ros, P. (2023). Detecting contextual network anomalies with graph neural networks. arXiv Preprint arXiv:2312.06342.
17. Lyu, S., Wang, K., Wei, Y., Liu, H., Fan, Q., & Wang, B. (2023). GNN-based advanced feature integration for industrial control system anomaly detection. ACM Transactions on Intelligent Systems and Technology, 15(1), 1–24.
18. Gajula, S. (2024). Adaptive zero trust architecture for securing financial microservices. Computer Fraud & Security, 643-655.
19. Miao, G., Wu, G., Zhang, Z., Tong, Y., & Lu, B. (2023). ADDAG-AE: Anomaly detection in dynamic attributed graphs based on graph attention networks and LSTM autoencoders. Electronics, 12(13), 2763.
20. Mir, A. A., Zuhairi, M. F., Musa, S., Alanazi, M. H., & Namoun, A. (2024). Variational graph convolutional networks for dynamic graph representation learning. IEEE Access, 12, 161697–161717.
21. Gajula, S. (2023). A Review of Anomaly Identification in Finance Frauds using Machine Learning System. International Journal of Current Engineering and Technology, 13(06).
22. Carletti, V., Foggia, P., Rosa, F., & Vento, M. (2025). Detecting malicious IoT network communication through graph neural networks in real-world conditions. Pattern Recognition Letters, 189, 92–98.
23. OPTIMAL Research Group. (2026). OPTIMAL: Unsupervised network intrusion detection model based on optimized graph neural network and graph contrastive learning. Computer Networks, 280, 112169.
24. Mendoza, M., Tesconi, M., & Cresci, S. (2020). Bots in social and interaction networks: Detection and impact estimation. ACM Transactions on Information Systems, 39(1), 1–28.
25. Diukarev, V., & Starukhin, Y. (2024). Proposed methods for preventing overfitting in machine learning and deep learning. Journal of Artificial Intelligence Research, 71, 215–230.
26. Chiranjeevi, V. R., & Malathi, D. (2024). Anomaly Graph: Leveraging dynamic graph convolutional networks for enhanced video anomaly detection in surveillance and security applications. Neural Computing and Applications, 36(20), 12011–12028.
27. Subramanian, V. K., Bhambri, S., & Gajula, S. (2025, April). Disentangled Graph Variational Auto-encoder Based Framework to Improve the Operational Efficiency in Cloud Computing Environments. In International Conference on Computer Vision and Robotics (pp. 396-407). Cham: Springer Nature Switzerland.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Bishop International Journal of Mathematics and Computer Science
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
