Vehicle-mounted CAN bus self-adaptive intrusion detection method based on message periodic characteristics

Abstract

The invention discloses a vehicle-mounted CAN bus self-adaptive intrusion detection algorithm based on a message periodic characteristic. The overall implementation process of the method is as follows: firstly, a detection node receives a message of an identifier IDj and records message receiving time, n receiving periods are calculated, the mean value and the maximum value of the receiving periods are calculated, and an intrusion detection threshold value is determined; in order to prevent false alarm, a small amount of time margin needs to be additionally added when a detection threshold isset; the messages of the identifier IDj are received, a time interval between two adjacent messages is calculated, and if the time interval exceeds a set threshold value, an alarm is given. Accordingto the method, whether the CAN bus in the vehicle is abnormally invaded or not can be detected, early warning is conducted, and the safety of the vehicle in the running process is improved. Accordingto the method disclosed by the invention, the detection threshold in the existing literature is optimized, and the determination rule of the detection threshold is formulated, so that the detection precision is further improved, and the injection type attack and the interruption type attack of the CAN bus message can be effectively detected.

Description

technical field [0001] The invention relates to a vehicle intrusion detection method, in particular to a vehicle CAN bus self-adaptive intrusion detection method based on message period characteristics. Background technique [0002] In recent years, vehicles have shown a trend of intelligence and networking. More and more electronic control units (ECU, Electronic Control Unit) are installed inside the vehicle to replace the original mechanical structure. With the increase of external communication interfaces, networked vehicles also introduce potential network security threats. The ECU installed in the vehicle can be remotely hacked through the network, which may cause the vehicle to malfunction, thereby threatening the life safety of the driver or passengers. How to avoid or mitigate these network security threats is an urgent task for the development of existing intelligent networked vehicle technology. [0003] Different from the traditional network security intrusion d...

AI Technical Summary

Problems solved by technology

This method is a lightweight intrusion detection algorithm for vehicle networks, which solves the problem of limited computing power of the equipment ECU

Images