A method of network intrusion anomaly detection based on machine learning

Abstract

The invention belongs to the technical field of network security, and relates to a machine learning-based network intrusion anomaly detection method, comprising the following steps: (1) classifying data feature attributes, (2) classifying target attributes in a data set according to traditional network intrusion categories Mapping, (3) reducing the dimensionality of the sample features in the data, (4) using the processed data set to train a multi-classification model for network requests, (5) using the test set data to evaluate the trained classification model. A network intrusion anomaly detection method based on machine learning of the present invention cooperates with feature processing and normalization technology to preprocess data, constructs an SVM model to realize efficient detection of network anomaly attacks, and solves traditional rule-based detection The method faces the problems of high maintenance cost and the need to update filtering rules in real time.

Description

technical field [0001] The invention relates to a machine learning-based network intrusion anomaly detection method, which belongs to the technical field of network security. Background technique [0002] With the deepening and promotion of wireless and mobile networks, more and more smart devices (mobile phones, TVs and other devices) rely on computer systems and the Internet, wireless networks (such as Bluetooth and Wi-Fi) and the Internet of Things, information The security situation is getting tougher by the day. Recently, network security incidents have occurred frequently, and network attacks have intensified. However, the network security defense technology is relatively traditional, the development of intelligent equipment lags behind, the real integration of network security and big data has not been fully realized, and the protection of key information infrastructure is also waiting to solve a series of bottleneck problems. Network intrusion detection refers to t...

AI Technical Summary

Problems solved by technology

However, due to the limitations of people's understanding of IT logic, they can only design IT systems by completing computing tasks, and there must be flaws in logic, making it difficult to deal with attacks by humans using flaws

Therefore, the traditional detection technology of changing the rule set through manual maintenance is not only inefficient, but also has a large maintenance cost, which has great defects.

Images