Internet of things intrusion detection method based on combination of decision tree and self-similar model

Abstract

The invention discloses a method for intrusion detection of the Internet of Things based on the combination of a decision tree and a self-similar model, including: S1, selecting a suitable data set; S2, generating a decision tree, first creating a tree, and the root node contains all samples Attribute information, adopt the minimum loss function strategy, and gradually deepen the decision tree; use the same method to generate K such decision trees; S3, use the decision tree generated in step S2 to analyze and process the test set prepared in step S1, so that Judging the intrusion status of the current state of the Internet of Things; S4. Establishing the histogram of the current state and the historical state of the Internet of Things data in the same period, using the self-similarity theory to set a suitable mathematical model, and judging whether there is an abnormal phenomenon in the current Internet of Things data. The invention mainly combines a decision tree algorithm and a self-similar model, avoids using a single detection method and fails to detect hidden intrusion behaviors, and makes the intrusion detection of the Internet of Things more comprehensive and accurate.

Description

technical field [0001] The invention relates to the technical field of Internet of Things security, in particular to an Internet of Things intrusion detection method based on the combination of a decision tree and a self-similar model. Background technique [0002] In the information age, we can feel the rapid development of the Internet and information technology in recent years. As an important part of the new generation of information technology, the Internet of Things is called the third wave of the development of the world information industry after computers and the Internet. Because of the advantages of low power consumption, easy deployment, and many node devices, the Internet of Things has led to the continuous expansion of the scale of the Internet of Things industry, and hundreds of millions of devices have been connected to the Internet of Things. The contradiction between the rapidly developing IoT industry and security issues is becoming more and more serious. ...

AI Technical Summary

Problems solved by technology

[0005] Existing intrusion detection methods basically analyze and detect network information in the current state, without comparing the current state of the network with the historical state of the same period, resulting in failure to detect some hidden intrusion behaviors

Images