Malicious node physical layer detection method and system based on automatic labeling and learning

Abstract

The invention relates to the technical field of communication safety, and discloses a malicious node physical layer detection method and detection system based on automatic labeling and learning. According to the detection method, the type of an access node in a network is identified based on a physical layer authentication strategy of channel difference, and malicious nodes initiating clone attacks and Sybil attacks can be detected at the same time; corresponding labels are automatically injected according to the types of the access nodes, so that the problem of manually injecting attack labels is solved, and the difficulty of lacking attack label samples when a supervised machine learning algorithm is used for channel authentication is solved; attack label samples are automatically injected by utilizing physical layer channel difference and setting a threshold method, and an offline label sample set is provided for a machine learning algorithm, so that automatic label injection and learning are realized, and the malicious node detection rate of an access node is improved. According to the method, the problem that the edge calculation node detects malicious nodes of various industrial wireless devices in an asymmetric scene of the industrial edge calculation Internet of Things can be effectively solved.

Description

technical field [0001] The present invention relates to the technical field of communication security, in particular, to a physical layer detection method for malicious nodes based on automatic labeling and learning, a physical layer detection system for malicious nodes based on automatic labeling and learning, and a method based on automatic labeling and learning A learned malicious node physical layer detection device. Background technique [0002] There are a large number of attacks in the edge computing industrial scenario. Once the system is attacked, the consequences will be disastrous. For example, attackers launch clone node attacks in unsupervised industrial wireless scenarios. The attacker first captures the legitimate node, steals the ID, key and data information of the legitimate node, and then deploys a large number of clone nodes in different locations in the industrial network, and uses the clone node to capture all the information of the legitimate node. Cl...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a malicious node physical layer detection method and system based on automatic labeling and learning to solve the above-mentioned problem of injecting labels into machine learning offline sample sets in attack detection and the problem of low detection rate of malicious nodes

Images