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

A can bus data anomaly detection method for multiple attack methods

A CAN bus and data anomaly technology, applied in the field of vehicle in-vehicle network anomaly detection, can solve the problem of insufficient sensitivity of local abnormal data, and achieve the effect of avoiding multiple data processing, fast response speed and fast processing speed

Active Publication Date: 2021-11-16
BEIHANG UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The anomaly detection method based on the isolation forest algorithm can effectively identify the data of the global anomaly, but it is not sensitive enough to the local anomaly data

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
  • A can bus data anomaly detection method for multiple attack methods
  • A can bus data anomaly detection method for multiple attack methods
  • A can bus data anomaly detection method for multiple attack methods

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with aspects of the present application as recited in the appended claims.

[0052] The terminology used in this application is for the purpose of describing particular embodiments only, and is not intended to limit the application. As used in this application and the appended claims, the singular forms "a", "the", and "the" are intended to include the plural forms as well, unless the context clearly dictates otherwise. It should also be understood that the term...

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

A CAN bus data anomaly detection method for multiple attack methods, which is divided into two stages: normal data set establishment and anomaly detection. In the isolated forest training stage, a normal data data set is formed, and the identification is calculated according to a sliding window with a fixed number of messages. According to the information entropy of the ID, the normal information entropy and the data corresponding to each ID in the sliding window are used to train the isolated forest; in the abnormal detection stage, the abnormal score is calculated for the ID with a fixed number of messages in the sliding window and the data of different IDs, and whether to proceed Exception Alert Decisions. The vehicle CAN data anomaly detection model based on information entropy and the isolated forest framework proposed by the present invention can detect a variety of attack methods against the CAN bus, and by improving the calculation method of the abnormal score in the isolated forest algorithm, the original calculation method is avoided. The shortcomings of local anomaly insensitivity, and then achieve anomaly detection with high efficiency and accuracy, which is conducive to safe driving and normal work of the car.

Description

technical field [0001] The invention relates to a vehicle-vehicle network anomaly detection technology, in particular to an isolation forest-based data anomaly detection method of a vehicle CAN bus network. Background technique [0002] With the rapid development of automobile intelligence and networking, automobile information security issues occur frequently. At present, attackers can carry out physical attacks and remote attacks through the interfaces between the car and the outside world, including OBD, charging interface, APP and wireless access interface. Attackers use replay, DOS, tampering, fuzz and other attack methods to invade the vehicle network, and then gain control of the vehicle or interfere with the normal operation of the vehicle, causing serious consequences such as loss of control of the vehicle. The most widely used in-vehicle network is the CAN (Controller Area Network) bus. The CAN bus has the characteristics of broadcast transmission, message arbitra...

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 Patents(China)
IPC IPC(8): H04L29/06H04L12/40
CPCH04L12/40H04L63/1416H04L63/1425H04L63/1458H04L63/1466H04L2012/40215
Inventor 田大新闫慧文段续庭周建山韩旭郎平郝威龙科军刘赫拱印生
Owner BEIHANG UNIV