Adaptive intrusion detection method for vehicle can bus based on message cycle characteristics

Abstract

The invention discloses a vehicle-mounted CAN bus adaptive intrusion detection algorithm based on message cycle characteristics. The overall implementation process of the method is as follows: first, the detection node receives the identifier ID j and record the message receiving time, calculate n receiving cycles, calculate the average value and maximum value of receiving cycles, and determine the intrusion detection threshold; in order to prevent false alarms, a small amount of time margin needs to be added when setting the detection threshold. Then receive the identifier ID j messages, calculate the time interval between two adjacent messages, and if it exceeds the set threshold, an alarm will be issued. The method of the invention can detect whether the CAN bus in the vehicle is invaded abnormally and give an early warning, thereby improving the safety of the vehicle during driving. The method of the invention optimizes the detection threshold in the existing literature, formulates the determination rule of the detection threshold, thereby further improving the detection accuracy, and can effectively detect the injection type attack and the interruption type attack of the CAN bus message.

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