An N-gram Based Deep Learning Method for Network Traffic Classification

摘要

Various attacks have become the main threat in the Internet world. Traffic classification is the first step in network exception detection or network-based intrusion detection systems, and plays an important role in the field of network security. With the development of Internet technology, the source and complexity of network attacks are getting higher and higher, making it difficult for traditional anomaly detection systems to effectively analyze and identify malicious traffic. In recent years, the method of deep learning has been widely used in the field of traffic recognition, and the characteristics of traffic data can be automatically identified. Because of the size limit of the input data of the neural network, the flow data needs to be trimmed to feed into the network for learning, so the neural network cannot learn the characteristics of the traffic data well. In this paper, we propose an N-gram-based data processing method to convert the raw traffic data into N-gram features to represent more information. Then our method uses a detector based on convolutional neural network (CNN) to classify and detect data. Our experiments show that the detection accuracy of using N-gram feature data is better than the method using raw traffic. This method can more effectively detect malicious traffic data.