An Anomaly Detection Model for CAN Networks Based on CNN and Transformer

Modern automobiles consist of several electronic control units (ECUs) that communicate with each other via the control area network (CAN) protocol. However, the CAN bus is susceptible to the risks associated with various attacks caused by the lack of encryption and certification mechanisms. To eliminate potential safety risks in vehicles, this paper proposes an anomaly detection system based on convolutional neural network (CNN) and transformer. Additionally, the ant-lion optimization (ALO) algorithm was introduced to adaptively adjust the receptive field size, thereby better capturing long-term dependencies in the input sequence data. We conducted tests on the car hacking dataset and evaluated the performance of multiple anomaly detection models on four metrics. The experiment shows that the method proposed in this article is efficient in detecting network attacks.