A campus network intrusion detection method and system

Abstract

The embodiment of the invention discloses a campus network intrusion detection method and system. The method includes: introducing labeled attack traffic into unlabeled campus network traffic to obtain a campus network hybrid data set; extracting campus network hybrid data sets from the campus network hybrid data set Traffic characteristics of web users visiting webpages and traffic characteristics of introduced attacks; assign random initial weight values ​​to the characteristics, and obtain the optimal weight of each characteristic through the optimal weight selection method based on genetic algorithm; according to the characteristics and characteristics of the optimal weight Divide the campus network mixed data set into normal clusters and abnormal clusters, filter the normal clusters to simplify the data, then perform a second clustering on the abnormal clusters, and analyze the campus network traffic in the abnormal clusters after clustering. Analysis: Calculate the detection rate of incoming attack traffic and the detection rate of campus network attack traffic, and generate detection results. The invention can well detect the attack behavior in the unlabeled data set, and improve the accuracy and reliability of the campus network intrusion detection.

Description

technical field [0001] The embodiments of the present invention relate to network security technologies, and in particular, to a campus network intrusion detection method and system. Background technique [0002] Network intrusion detection system is an active security protection measure, which can detect possible malicious activities and attack behaviors in the network, and is an effective supplement to traditional security products. With the rapid development of the Internet, the network traffic generated by various devices and hosts increases exponentially, which inevitably brings more challenges to the intrusion detection system. Therefore, how to efficiently divide a large amount of data into different categories by features becomes particularly important. We can further judge normal behavior and abnormal behavior based on the category information. [0003] With the continuous development of informatization in colleges and universities, campus network traffic has incr...

AI Technical Summary

Problems solved by technology

[0005] In view of this, the embodiment of the present invention provides a campus network intrusion detection method and system, which solves the problem of attack traffic detection of unlabeled data sets

Images