Network flow anomaly detection method based on intuitionistic fuzzy time series graph mining

Abstract

The invention discloses a network flow anomaly detection method based on intuitionistic fuzzy time series graph mining. The method comprises the following steps: step 1, constructing an IFTS graph; step 2, IFTS graph mining; and step 3, determining an anomaly judgment criterion. The method has the beneficial effects that an intuitionistic fuzzy time sequence diagram is constructed, so that the vertex relationship information in the diagram is comprehensively mined and fully utilized, and the network traffic abnormality can be more accurately detected. The method firstly converts original one-dimensional network flow prediction into more accurate five-dimensional prediction by combining information entropy and an IFTS prediction technology; in addition, heuristic variable-order IFTS prediction not only has efficient prediction performance on an incomplete data set, but also can enable a prediction result to be closer to reality. A complete graph established by using a more accurate prediction result can reflect the change of the flow attribute more accurately, so that a more accurate exception report is obtained through frequent sub-graph mining.

Description

technical field [0001] The invention belongs to the technical field of data mining, and in particular relates to a method for detecting abnormal network traffic. Background technique [0002] A network traffic anomaly is a situation where the behavior of traffic in a network deviates from its normal behavior. In order to ensure the security and stability of the network and maintain its efficient operation, network managers need to adopt appropriate technologies to describe and analyze possible anomalies in the network and give early warnings. This is network traffic anomaly detection. With the rapid development and wide application of Internet technology, various network attack technologies emerge in an endless stream, and new network security issues continue to emerge. Therefore, traffic anomaly detection technology has also become a hot spot that has always been concerned and researched. been applied to this field. [0003] At present, the commonly used methods mainly in...

AI Technical Summary

Problems solved by technology

The first two methods do not consider the relationship between the vertices in the graph, and the third method does not consider the relationship between the vertices in the graph comprehensively.

To sum up, most of the current existing methods are implemented based on one-dimensional network traffic prediction, the prediction results are not accurate enough, there is a large deviation from the actual traffic, and the accuracy of the obtained network theoretical detection report is not high

Images