Anomaly detection method for vehicle-mounted CAN bus

The invention discloses an anomaly detection method for a vehicle-mounted CAN bus, and belongs to the technical field of information security. The invention provides an anomaly detection method of a vehicle-mounted CAN bus for message data bits of the vehicle-mounted CAN bus. According to the characteristics of the data bits, the data bits of the vehicle-mounted CAN bus message are divided into eight characteristics which respectively represent different instruction meanings and carry important control information, and the method is particularly important for anomaly detection of the data bits. Abnormality detection of CAN message data can be regarded as a dichotomy problem, normal data and abnormal data in machine learning. According to the method of the support vector machine, classification with small errors can be obtained through limited training samples, and the classification accuracy is high. According to the invention, a support vector machine (SVM) method is adopted to realize anomaly detection of t