Unknown Binary Protocol Recognition Algorithm Based on One Class of Classification and One-Dimensional CNN

In order to solve the problem that there are a large number of unknown protocols on network, which affect network management and security in varying degrees, an binary protocol identification method is proposed. On premise center cluster obtained by clustering algorithm, for traffic identified combining one-class classification with one-dimensional CNN technology. At first, class algorithm used select protocols, then, labeled data train model, classified packets directly as input convolution neural network. After finally identified. The experimental results show proposed recognition better than traditional SVM algorithms, maximum frequency pooling method.