Network intrusion detection method and device based on deep learning and storage medium

Abstract

The invention discloses a network intrusion detection method and device based on deep learning and a storage medium, which are used for improving the network intrusion detection efficiency and detection precision. The deep learning-based network intrusion detection method comprises the steps of extracting original data from a to-be-detected network connection; preprocessing the original data, andconverting the preprocessed original data into first picture format data; and based on the first picture format data obtained by converting the original data, performing detection by using a preset network intrusion detection model, the network intrusion detection model being obtained by training network connection sample data in a training data set by using a convolutional neural network.

Description

technical field [0001] The present invention relates to the technical field of computer networks, in particular to a network intrusion detection method, device and storage medium based on deep learning. Background technique [0002] The Internet has now become an indispensable part of people's daily life, and at the same time, many network attacks have emerged that threaten the security of the network. Therefore, how to protect network security has become a hot research field. Intrusion detection is an important measure to protect network security. By analyzing network traffic data, it can determine whether the network is under threat and attack, and can determine the type of attack. According to the detection results, we can take targeted protective measures to protect the network. Safety. [0003] Network intrusion detection methods generally include two steps: feature selection and classification. Feature selection is a key factor for selecting and distinguishing data c...

AI Technical Summary

Problems solved by technology

The classifier trains the selected feature data. Many classification algorithms in machine learning can be used to classify network traffic, such as SVM (support vector machine), DTs, ANN (artificial neural network), Bayes (Bayesian), etc. However, machine learning algorithms rely on the quality of features selected by feature selection algorithms, and the accuracy of detection results largely depends on the selected features. Moreover, with the rapid growth of network traffic data, the real-time requirements for network security intrusion detection are even higher. High, protective measures must be taken within a limited time to ensure network security, while traditional machine learning algorithms have the problem of low detection efficiency and detection accuracy when processing large amounts of data

Images