Intrusion detection method based on convolutional neural network and lightweight gradient elevator

Abstract

The invention discloses an intrusion detection method based on a convolutional neural network and a lightweight gradient elevator, and relates to an intrusion detection technology in the field of network security, and the method comprises the steps: data preprocessing, wherein the data preprocessing process comprises data type conversion, an oversampling technology and image data conversion; feature selection: using a CNN model to select features; and intrusion detection classification: performing classification by using a Light GBM algorithm. According to the method, the difficulty of intrusion detection analysis caused by imbalance, high dimension and nonlinearity of data is overcome, so that the method shows better performance in multi-dimensional evaluation indexes such as accuracy, precision rate and missing report rate.

Description

technical field [0001] The present invention relates to intrusion detection technology in the field of network security, especially an intrusion detection method based on convolutional neural network and lightweight gradient boosting machine, which is used for processing complex unbalanced data and high-dimensional data limitations. Background technique [0002] With the development of network technology, the rapid growth of network scale not only brings convenience to people, but also brings risks and challenges. Problems such as the theft of private data and the encroachment of server resources have brought great troubles to people. In order to deal with many subsequent problems, intrusion detection technology came into being. For example, in 2017, hackers exploited Windows system vulnerabilities to cause 100,000 organizations around the world to be attacked by Bitcoin ransomware. In 2019, the hacker organization Fxmsp invaded three anti-virus companies, extracted the s...

AI Technical Summary

Problems solved by technology

In 2019, the hacker organization Fxmsp invaded three anti-virus companies, extracted the source code of anti-virus software, and caused huge losses to the companies

However, due to the influence of more parameter settings and complex calculations, there are still problems of low classification accuracy and high false alarm rate.

Images