IoVST: An anomaly detection method for IoV based on spatiotemporal feature fusion

Abstract

In the Internet of Vehicles (IoV) based on Cellular Vehicle-to-Everything (C-V2X) wireless communication, vehicles inform surrounding vehicles and infrastructure of their status by broadcasting basic safety messages, enhancing traffic management capabilities. Since anomalous vehicles can broadcast false traffic messages, anomaly detection is crucial for IoV. State-of-the-art methods typically utilize deep detection models to capture the internal spatial features of each message and the timing relationships of all messages in a sequence. However, since existing work neglects the local spatiotemporal relationship between messages broadcasted by the same vehicle, the spatiotemporal features of message sequences are not accurately described and extracted, resulting in inaccurate anomaly detection. To tackle these issues, a message attribute graph model (MAGM) is proposed, which accurately describes the spatiotemporal relationship of messages in the sequence using attribute graphs, including the internal spatial features of messages, the temporal order relationship of all messages, and the temporal order relationship of messages from the same vehicle. Furthermore, an anomaly detection method for IoV based on spatiotemporal feature fusion (IoVST) is proposed to detect anomalies accurately. IoVST aggregates the local spatiotemporal features of MAGM based on Transformer and extracts the global spatiotemporal features of message sequences through global time encoding and the self-attention mechanism. We conducted experimental evaluations on the VeReMi extension dataset. The F1 score and accuracy of IoVST are 1.68% and 1.92% higher than the optimal baseline method. The detection of every message can be accomplished in 0.7185 ms. In addition, the average accuracy of IoVST in four publicly available network intrusion detection datasets is 7.77% higher than the best baseline method, proving that our method can be applied well to other networks such as traditional IT networks, the Internet of Things, and industrial control networks.