Internet of Things intrusion detection method based on self-supervised learning and self-knowledge distillation

Abstract

The invention discloses an Internet of Things intrusion detection method based on self-supervised learning and self-knowledge distillation, and the method comprises the steps: carrying out the first-stage training of a lightweight intrusion detection model: determining the network structures of an online network and a target network, and initializing the parameters of the target network through the weight of the online network; respectively inputting the enhanced data into the online network and the target network for training; adjusting an error in a training process according to a loss value obtained by a loss function of self-supervised contrast learning until the online network reaches convergence; storing the weight of the online network to the local for second-stage training; in the second stage of training, the network structure of the student network is determined, and the online network weight is loaded to the teacher network; inputting the enhanced data into a student network and a teacher network for training; adjusting the error of the training process according to the loss value obtained by the loss function of the self-knowledge distillation until the student network reaches convergence; and storing the student network weight to the local for lightweight intrusion detection model testing. The intrusion detection speed is increased, and the complexity is low.

Description

Technical field [0001] The invention is the field of Internet of Things technology, which involves a method of Internet of Things invasion testing based on self -supervision learning and self -knowledge distillation. Background technique [0002] The Internet of Things is an extension of the Internet and the Internet connected by everything. Its core and foundation are still the Internet. It is an extension and expansion of the Internet based on the Internet. The Internet of Things is a network of information exchange and communications through the agreed agreement to connect any item to the Internet in accordance with the agreed agreement to realize the network of intelligent identification, positioning, tracking, monitoring and management of items. The rise of IoT technology has changed the new trend of the information world, and is considered the third wave of information development after computers and the Internet. Today, IoT technology is quietly changing our lifestyle and ...

AI Technical Summary

Problems solved by technology

[0004] In recent years, a large number of intrusion detection systems based on machine learning and deep learning have been widely used in the attack detection of IoT devices. However, there are still many challenges in detecting abnormal traffic in IoT.

First of all, network nodes in the Internet of Things are usually deployed in devices with limited resources (such as limited power, limited computing, communication and storage capabilities, etc.); The assistance of network security experts can determine whether network traffic is a new attack method; in addition, IoT networks use different protocol stacks and standards, these requirements make intrusion detection systems need to design corresponding security mechanisms

Therefore, a good IoT intrusion detection system needs to meet the characteristics of lightweight, real-time and unsupervised. However, most of the existing intrusion detection systems only meet one of the three characteristics, and few of them meet the three characteristics. Internet of things intrusion detection system

Images