Big data intrusion detection method based on weighted hidden naive Bayesian model

Abstract

The invention discloses a big data intrusion detection method based on a weighted hidden naive Bayesian model, and the detection method comprises the following steps: online collection: transmitting network intrusion virus data in big data to a weighted hidden naive Bayesian model database, and carrying out the data conversion of the intrusion virus attributes to obtain an intrusion attribute information table; offline construction: collecting, obtaining and preprocessing offline data packets in the equipment through mitmproxy packet capture software to obtain an offline data packet attribute set. According to the invention, the virus attributes are subjected to multi-level classification through a powerful database, classification is integrated to form the attribute matrix, and the attribute matrix is comprehensively accessed through the Bayesian model, so that compared with a traditional WAF technology, website intrusion is more accurate and comprehensive, the probability of missing detection and false detection can be reduced, and the passing rate of viruses with hidden attributes and unknown attributes can be reduced; model learning is performed by capturing a data packet, so that the performance overhead of a server is reduced, and various intrusion attack means can be identified.

Description

technical field [0001] The invention relates to the technical field of big data intrusion detection, and more specifically relates to a big data intrusion detection method based on a weighted hidden naive Bayesian model. Background technique [0002] With the advent of the era of big data, the types of data actually collected are becoming more and more diverse, and there are often irrelevant or redundant attributes in these data, which will have some negative effects on the classification results. In order to solve the above problems, this topic is based on the naive Bayesian model, and after researching it, it proposes an improvement plan, proposes an improvement to the attribute selection algorithm (CFS) and an improved weighted hidden naive Bayesian model, and puts the model Applied to the big data intrusion detection problem. [0003] Naive Bayesian method is a classification method based on Bayesian theorem and the independent assumption of characteristic conditions [1...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a large data intrusion detection method based on the weighted hidden naive Bayesian model, which solves the problem of low ability to detect unknown types of virus attacks and the slow detection speed of multi-attribute intrusion viruses in the intrusion detection technology. The problem of the problem, to meet the actual use needs

Images