With the development of intelligent and networking technology in automobile, the malicious attacks against in-vehicle CAN networks are increasing day by day, and the problem of information safety in automobile is aggravated. In this regard, this paper analyzes the security loopholes and threats which the CAN bus faced, put forward a kind of anomaly detection algorithm for vehicle CAN bus. The method uses support vector machine algorithm to distinguish between normal message and abnormal message, so as to realize the CAN bus anomaly detection. Theoretical and experimental studies show that this method can effectively detect abnormal packets in the CAN bus with a detection rate of over 90%, which can effectively resist malicious attacks such as tampering and cheating on the vehicle CAN bus.