Unlock instant, AI-driven research and patent intelligence for your innovation.

Method and device for identifying abnormal traffic of Internet of Vehicles based on instruction sequence

A technology of abnormal traffic and instruction sequence, applied in the direction of secure communication device, neural learning method, biological neural network model, etc., can solve the problem of single input object of protocol specification

Active Publication Date: 2022-04-29
山西省信息通信网络技术保障中心 +2
View PDF12 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention aims to solve the problem that the existing technology cannot combine the protocol specification of the Internet of Vehicles protocol and the single input object, and provides a method and device for identifying abnormal traffic in the Internet of Vehicles based on the instruction sequence. Through in-depth analysis of the data encapsulation method and The message structure extracts the effective instruction load at the specified offset position of the data stream, forms the Internet of Vehicles instruction load sequence, converts the load sequence into a picture, inputs the convolutional neural network (CNN) for training, and establishes an abnormal traffic identification model

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method and device for identifying abnormal traffic of Internet of Vehicles based on instruction sequence
  • Method and device for identifying abnormal traffic of Internet of Vehicles based on instruction sequence
  • Method and device for identifying abnormal traffic of Internet of Vehicles based on instruction sequence

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0080] Such as Figure 1-2 As shown, a method for identifying abnormal traffic in the Internet of Vehicles based on instruction sequences includes the following steps:

[0081] S1. Data traffic collection and analysis for training: The traffic collection module captures the normal traffic and abnormal traffic in the Internet of Vehicles traffic through the packet capture tool and outputs them as training data traffic to the data preprocessing module. The normal traffic is the interaction between the vehicle terminal and the cloud service platform Traffic, abnormal traffic is collected from the cloud service platform;

[0082] Normal traffic includes registration traffic, authentication traffic, heartbeat traffic, map traffic query traffic, upload traffic, assisted driving information traffic, and entertainment information service traffic. Abnormal traffic includes intrusion traffic, scanning detection traffic, and DDOS traffic collected by the cloud service platform. Both tra...

Embodiment 2

[0102] Such as Figure 1-2 As shown, a method for identifying abnormal traffic in the Internet of Vehicles based on instruction sequences includes the following steps:

[0103] 1. Data traffic collection and analysis, mainly to capture the interactive data generated during the communication process of the Internet of Vehicles, including the collection of interactive traffic information between the vehicle terminal and the cloud service platform. The abnormal traffic is mainly the intrusion and detection traffic collected on the cloud service platform;

[0104] 2. Vehicle networking traffic preprocessing, split the mixed traffic into multiple groups of session flows with different source IPs through triplets (source IP, destination IP, destination port);

[0105] 3. Sequentially divide the data streams of different source IPs into single streams according to the quintuple (source IP, source port, destination IP, destination port, transport layer protocol), and extract them at t...

Embodiment 3

[0130] Such as image 3 As shown, a device for identifying abnormal traffic in the Internet of Vehicles, including a traffic collection module, a data preprocessing module, a rule extraction module and a model training module connected in sequence;

[0131] The traffic acquisition module is used to capture the normal traffic and abnormal traffic in the Internet of Vehicles traffic through the packet capture tool and output it to the data preprocessing module as the data traffic for training;

[0132] Normal traffic includes registration traffic, authentication traffic, heartbeat traffic, map traffic query traffic, upload traffic, assisted driving information traffic, and entertainment information service traffic, and abnormal traffic includes intrusion traffic collected by the cloud service platform, scanning detection traffic, and DDOS traffic;

[0133] The data preprocessing module is used to receive training data traffic and the Internet of Vehicles traffic to be detected, ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention provides an Internet of Vehicles abnormal traffic identification method and device based on an instruction sequence, and the method comprises the steps: extracting an effective instruction load at a specified offset position of a data stream through deep analysis of a data packaging mode and a message structure of an Internet of Vehicles protocol, forming an Internet of Vehicles instruction load sequence, converting the load sequence into a picture, and carrying out the recognition of the abnormal traffic of the Internet of Vehicles. And inputting a convolutional neural network CNN for training, and establishing an abnormal traffic recognition model. According to the method, on the basis of the characteristics of an Internet of Vehicles protocol, instructions and instruction sequences in the current mainstream Internet of Vehicles protocol serve as recognition features of normal and abnormal traffic, the features are further strengthened and converged in combination with a convolutional neural network, IP-level session streams serve as training samples, and compared with a traditional single-stream sample, the method has the advantage that the recognition efficiency is improved. Different instruction operations of the traffic in different time periods can be better reflected, and the time characteristics of the traffic are fully utilized.

Description

technical field [0001] The invention relates to the technical field of digital information transmission, in particular to a method and device for identifying abnormal traffic in the Internet of Vehicles based on instruction sequences. Background technique [0002] At present, my country's Internet of Vehicles agreements mainly include JT / T808, JT / T905, GB / T32960 and other agreements. Taking JT / T808 as an example, it is a standard agreement formulated by the Ministry of Transport, which stipulates that the satellite positioning system of road transport vehicles is compatible with Beidou. The communication protocol and data format between the vehicle terminal and the supervision / monitoring platform, including protocol basis, communication connection, message processing, protocol classification and description, and data format. [0003] The retrieved abnormal traffic of the Internet of Vehicles is mainly intrusion traffic, and its identification mainly adopts machine learning or...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): H04L69/22H04L69/06H04L9/40H04L67/12G06N3/04G06N3/08
CPCH04L69/22H04L69/06H04L63/1441H04L63/1458H04L67/12G06N3/08G06N3/045
Inventor 刘红雨孟强李彦君梁国光王碧扬王红涛李竞隆冰王飞游帅刘杰林飞易永波华仲锋阮伟军詹斯伟杨伦陈磊关振府栗志新
Owner 山西省信息通信网络技术保障中心