A novel QUIC traffic Classifier based on Convolutional Neural Networks
Abstract
Nowadays, network traffic classification plays an important role in many fields including network management, intrusion detection system, malware detection system, etc. Most of the previous research work concentrates on features extracted in the context of non-encrypted network traffic. However, these features are not compatible with all kind of traffic characterization. Google’s QUIC protocol (Quick UDP Internet Connection protocol) is developed robustly and implemented in many services of Google. Nevertheless, the emergence of this protocol imposes many obstacles for traffic classification due to the reduction of visibility for operators into network traffic, so the port and payload-based traditional methods cannot be applied to identify the QUIC-based services. To address this issue, we proposed a novel technique for traffic classification based on the convolutional neural network which combines the feature extraction and classification phase into one system. The proposed method uses the NetFlow and packet-based features to improve the performance. In comparison with current methods, the proposed method can identify some kind of QUIC-based services such as Google Hangout Chat, Google Hangout Voice Call, YouTube, File transfer and Google play music. Besides, the proposed method can achieve the micro-averaging F1-score of 99.24 percent.