Network intrusion detection method and system based on ensemble learning

Abstract

The invention discloses a network intrusion detection method and system based on ensemble learning, and the method comprises the steps: employing a WGAN-based network attack traffic data enhancement method in a data preprocessing stage, generating attack samples, and increasing the number of the samples, thereby solving a problem that a few attack types are ignored by a learner algorithm; generating a plurality of learners by adopting a Stacking algorithm in ensemble learning, and solving an over-fitting problem in ensemble learning in cooperation with a five-fold cross validation algorithm, so the classification accuracy of minority classes is greatly improved, and the overall class accuracy is slightly improved. The system mainly comprises four modules: a data acquisition module, a data preprocessing module, a data generation module and an intrusion detection module based on Stacking. According to the scheme, the minority class data is oversampled through the WGAN, the purpose of data rebalancing is achieved, the problem that the unbalanced data set classification performance is poor in an existing intrusion detection technology is solved through integrated learning, and the minority class and overall detection accuracy in network intrusion detection is improved.

Description

technical field [0001] The invention relates to the field of Internet security, in particular to a network intrusion detection method and system based on integrated learning. Background technique [0002] In recent years, my country's Internet penetration rate and the total number of netizens have steadily increased. The application of the Internet industry is closely related to people's daily life, and is changing the way people live, study and work. The rapid development of the Internet industry should also pay attention to various network security issues: DDoS attacks, mining activities, Web attacks, exploiting system vulnerabilities and other attacks have always existed in the Internet, and these attacks have caused huge Economic losses, and even a serious threat to national security and social stability. Intrusion detection is a branch of computer network security, aiming to detect computer network intrusion automatically and effectively. Many scholars and research ins...

AI Technical Summary

Problems solved by technology

At present, it is rarely used to solve the problem of network intrusion detection data imbalance, which provides a new idea for solving this problem

Images