Training method of intrusion detection network structure model

Abstract

The invention relates to a training method of an intrusion detection network structure model. The method comprises the following steps: acquiring an original data set; preprocessing the original data set to obtain a training data set; grouping the training data set according to a preset time length, and splicing data in each group into a two-dimensional array sample to obtain a first preset number of two-dimensional array samples; training a pre-constructed network structure model by using the first preset number of two-dimensional array samples, wherein the network structure is a convolutional neural network added with BAM; outputting a training result, wherein the training result is an intrusion detection network model. Therefore, the neural network and the attention mechanism are combined and introduced into the industrial control system, the data in the industrial control system are subjected to feature reordering to strengthen the effect of the attention mechanism neural network, and the data are input into the network for training after space-time splicing, so that the detection of deceptive attacks can be realized, and the calculation efficiency and performance can be improved, and the detection speed is further improved.

Description

technical field [0001] The present application relates to the technical field of industrial control data processing, in particular to a training method for an intrusion detection network structure model. Background technique [0002] With the rapid development of economy and society, the integration of industrialization and informatization continues to deepen, and industrial control systems are gradually moving from closed to open, and various security problems and risks are becoming more and more prominent. As a method that can effectively discover malicious intrusion behavior, intrusion detection occupies an important position in industrial control systems. [0003] In related technologies, there are many existing algorithms for intrusion detection, such as deep neural network algorithms, radial basis function neural network algorithms, and random forest algorithms. However, these algorithms only detect data at a certain point in time, and it is difficult to detect decept...

AI Technical Summary

Problems solved by technology

However, these algorithms only detect data at a certain point in time, and it is difficult to detect deceptive attacks, such as deviation attacks and geometric attacks.

Images