ABSTRACT Cooperative messaging in vehicular ad‐hoc networks (VANETs) enables safety‐critical functions such as collision avoidance, platooning, and traffic optimization. However, in dense urban traffic environments, rapidly changing topology and high‐volume broadcast messaging introduce vulnerabilities to spoofing, flooding, and falsified data injection. Traditional anomaly detection approaches, including basic machine learning or static rule‐driven models, are insufficient to capture the evolving spatial–temporal dependencies and message correlations inherent to mobile vehicular ecosystems. To overcome these limitations, this paper introduces graph neural network–enabled adaptive resilient intelligence for spatiotemporal event detection (GNN‐ARISE). A novel anomaly detection architecture integrating GNN‐based reasoning with traffic‐aware message intelligence. GNN‐ARISE comprises: (1) a Dynamic GNN Graph Constructor, continuously reshaping communication graphs using mobility signatures and message trust indices. (2) a Temporal Evolution Encoder, leveraging gated recurrent attention to model message propagation patterns over time. (3) a Resilient Anomaly Classifier, fusing graph embeddings and vehicle trust scoring for robust detection under real‐time constraints. Evaluation using dense VANET simulation datasets demonstrates that GNN‐ARISE improves detection accuracy by 21.2%, reduces false‐positive rates by 23.5%, and maintains processing latencies under 22 ms, outperforming baseline GNN and spatiotemporal learning models. The results highlight the value of integrating GNN‐based adaptive reasoning for securing next‐generation intelligent transportation communication infrastructures. The proposed method achieves the anomaly detection accuracy (86%–96%), FPR (6%–11%), detection latency of 45% and 125 ms, robustness under high node (82%–90%), attack type generalization capability (83%–87%).
Ahmed Zohair Ibrahim (Sun,) studied this question.