IOV intrusion attack detection method and system based on artificial intelligence behaviour analysis

Abstract

The invention relates to the technical field of networks, and discloses an IOV intrusion attack detection method and system based on artificial intelligence behaviour analysis. The method comprises the steps of: obtaining network access flow data, and reducing flow according to a communication protocol to obtain a network access ticket log; filtering the ticket log at least according to one or more characteristics in an APN, a number segment and an IOV APP; extracting access parameter characteristics and access behaviour characteristics by utilizing known IOV normal access data and abnormal intrusion attack data, and training by using an artificial intelligence classifier model; and, for real-time IOV access data, extracting access parameter characteristics and access behaviour characteristics, judging whether an intrusion attack occurs or not by using the trained classifier model, and correspondingly processing an intrusion attack behaviour. By means of the method and the system disclosed by the invention, whether an IOV vehicle is intruded by an external behaviour or not can be accurately judged.

Description

technical field [0001] The present invention relates to the field of network technology, in particular to a method and system for intrusion attack detection of Internet of Vehicles based on artificial intelligence behavior analysis. Background technique [0002] According to the "Intelligent Networked Vehicle Information Security White Paper" released by the China Association of Automotive Engineers in 2017, the penetration rate of China's intelligent driving passenger vehicles has reached 15% in 2015, and this figure is expected to reach 50% in 2019. Intelligent networked vehicles generally communicate through the mobile network through the vehicle sensor network, the vehicle intelligent terminal, the cloud TSP, and the owner's mobile APP, and the communication data is transmitted through the public network, so it also gives hackers an opportunity. Infiltration, intrusion, and attack to achieve illegal purposes. [0003] Hidden dangers of network security exist in all comp...

AI Technical Summary

Problems solved by technology

[0003] Hidden dangers of network security exist in all components of the Internet of Vehicles architecture. The network security protection of the Internet of Vehicles needs to be implemented through multiple layers of the cloud pipe end. Since the data of the Internet of Vehicles is usually transmitted in an encrypted manner, it is generally impossible to identify and analyze it on the pipe side of the mobile network The plaintext of the Internet of Vehicles data, the traditional intrusion detection method cannot judge the legality of the data

Images