Matching Algorithm for Data Similarity of Public Dataset of Network Intrusion Detection

In order to provide the basis for the improvement and optimization of the public network intrusion detection data set, a matching algorithm for data similarity of the KDD CUP ’ 99 data set is proposed in this paper. According to the characteristics of the feature record of the network flow of the data set, the structure is defined to save a complete network flow feature record. The sub-algorithm of reading flow feature record, constructing flow feature record queue, calculating flow feature record similarity, and matching data set similarity are designed for the process of data set similarity matching including reading, parsing, similarity calculation, and mutual matching. With the program based on the above matching algorithm, repeated experiments are carried out. The experiment result shows that the matching algorithm can calculate data similarity accurately.