Explainable Graph Neural Network Driven Anomaly Detection for Secure Routing in Vehicular Ad Hoc Networks
Journal of Computer and Communication Networks
Received On : 02 November 2025
Revised On : 09 January 2026
Accepted On : 12 January 2026
Published On : 15 January 2026
Volume 02, 2026
Pages : 001-012
Abstract
Vehicular Ad Hoc Networks (VANETs) are one of the main pillars of intelligent transportation systems of the next generation as they allow vehicles and roadside devices to communicate in real-time to exchange information about safety, traffic performance, and autonomous driving. Nevertheless, the extremely dynamic topology, unstable connectivity and vulnerability to cyber-attacks including blackhole, Sybil and denial-of-service attacks are major problems to routing security and reliability. Conventional anomaly detection techniques use fixed thresholds or rudimentary machine learning proxies which do not reflect more intricate spatiotemporal interactions or are not interpretable to make safety critical decision making. The proposed framework based on explaining graph neural networks (XGNN) in this paper is a proposal of an anomaly detection framework that can be used in secure routing within the VANETs. The model builds on the use of graph-based vehicle communication representations to combine the dynamic interactions of the nodes, and incorporates attention-seeking mechanisms to detect the influential features involved in abnormal behavior. An explainability post-hoc module is added to allow clear insight of what is being predicted by the model, which increases trust and makes it easier to support real time decisions. The realistic vehicular mobility data and simulation of attack situations are used to test the proposed framework. It has been shown experimentally that XGNN model can detect anomalies with an accuracy of 97.8 which is greater than the other traditional machine learning models like the SVM and Random Forest by 8-12. The proposed method will also decrease the false positive rates by 15 percent and increase the routing reliability by 20 percent when conditions are adverse. The explainability aspect also makes it possible to identify malicious nodes with high accuracy, which enhances the resilience of the network. This study adds a strong, understandable and high-performing solution to secure communication in VANET networks.
Keywords
VANETs, Explainable Graph Neural Network, Secure Communication, Secure Routing, Anomaly Detection.
- Z. Ibrahim, “Spatiotemporal Graph Neural Network‐Driven Anomaly Detection for Cooperative Vehicle Messaging in Dense VANET Corridors,” Transactions on Emerging Telecommunications Technologies, vol. 37, no. 4, Mar. 2026, doi: 10.1002/ett.70405.
- M. S. Aljumaily and S. J. Abdullah, “Deep Learning for Enhanced Anomaly Detection in Wireless Communication Networks using Channel State Information (CSI),” International Journal of Mechatronics, Robotics, and Artificial Intelligence, vol. 1, no. 2, pp. 105–114, Sep. 2025, doi: 10.33971/ijmrai.1.2.13.
- G.-Y. Yang, F. Wang, and K.-H. Yeh, “GNN-Enhanced Traffic Anomaly Detection for Next-Generation SDN-Enabled Consumer Electronics,” IEEE Transactions on Consumer Electronics, vol. 71, no. 4, pp. 10977–10985, Nov. 2025, doi: 10.1109/tce.2025.3620095.
- E. A. Aldhahri, A. A. Almazroi, M. H. Alkinani, M. Alqarni, E. A. Alghamdi, and N. Ayub, “GNN-RMNet: Leveraging graph neural networks and GPS analytics for driver behavior and route optimization in logistics,” PLOS One, vol. 20, no. 8, p. e0328899, Aug. 2025, doi: 10.1371/journal.pone.0328899.
- A. Naz, K. Verma, and G. Sikka, “GNN-TASR: Graph Neural Network based Trust Aware Secure Routing for LEO satellite network,” Ad Hoc Networks, vol. 187, p. 104223, Jun. 2026, doi: 10.1016/j.adhoc.2026.104223.
- R. Mavropodi, P. Kotzanikolaou, and C. Douligeris, “SecMR – a secure multipath routing protocol for ad hoc networks,” Ad Hoc Networks, vol. 5, no. 1, pp. 87–99, Jan. 2007, doi: 10.1016/j.adhoc.2006.05.020.
- A. Bazzi and A. Zanella, “Position based routing in crowd sensing vehicular networks,” Ad Hoc Networks, vol. 36, pp. 409–424, Jan. 2016, doi: 10.1016/j.adhoc.2015.06.005.
- S. Sarkar and R. Datta, “A secure and energy-efficient stochastic multipath routing for self-organized mobile ad hoc networks,” Ad Hoc Networks, vol. 37, pp. 209–227, Feb. 2016, doi: 10.1016/j.adhoc.2015.08.020.
- J.-H. Song, V. W. S. Wong, and V. C. M. Leung, “Secure position-based routing protocol for mobile ad hoc networks,” Ad Hoc Networks, vol. 5, no. 1, pp. 76–86, Jan. 2007, doi: 10.1016/j.adhoc.2006.05.010.
CRediT Author Statement
The author reviewed the results and approved the final version of the manuscript
Acknowledgements
Author(s) thanks to Sri Eshwar College of Engineering for research lab and equipment support.
Funding
No funding was received to assist with the preparation of this manuscript.
Ethics Declarations
Conflict of interest
The authors have no conflicts of interest to declare that are relevant to the content of this article.
Availability of Data and Materials
Data sharing is not applicable to this article as no new data were created or analysed in this study.
Author Information
Contributions
All authors have equal contribution in the paper and all authors have read and agreed to the published version of the manuscript.
Corresponding Author
Rights and permissions
This is an open access article distributed under the terms of the Creative Commons Attribution 4.0 International License (CC BY 4.0).
https://creativecommons.org/licenses/by/4.0/.
This license permits unrestricted use, sharing, distribution, reproduction, and adaptation in any medium or format, including for commercial purposes, provided that appropriate credit is given to the original author(s) and the source, a link to the license is provided, and any changes made are indicated.
Copyright
© 2026 Anandakumar Haldorai. The author(s) retain copyright of the work. The author(s) grant the Journal of Computer and Communication Networks (JCCN) and its publisher, Ansis Publications, the right of first publication and the right to identify itself as the original publisher of the article.
Cite this Article
Anandakumar Haldorai, “OExplainable Graph Neural Network Driven Anomaly Detection for Secure Routing in Vehicular Ad Hoc Networks”, Journal of Computer and Communication Networks, pp. 001-012, 2026, doi: 10.64026/JCCN/2026001.