Network traffic classification has great significance for network security, network management and other fields. However, in recent years, the use of VPN and TLS encryption had presented network traffic classification with new challenges. Due to the great performances of deep learning in image recognition, many solutions have focused on the deep learning-based method and achieved positive results. A traffic classification method based on deep learning is provided in this paper, where the concept of Packet Block is proposed, which is the aggregation of continuous packets in the same direction. The features of Packet Block are extracted from network traffic, and then transformed into images. Finally, convolutional neural networks are used to identify the application type of network traffic. The experiment is conducted using captured OpenVPN dataset and public ISCX-Tor dataset. The results shows that the accuracy is 97.20% in OpenVPN dataset and 93.31% in ISCX-Tor dataset, which is higher than the state-of-the-art methods. This suggests that our approach has the ability to meet the challenges of VPN and TLS encryption.

Communities are an important feature of real-world networks that can reveal the structure and dynamic characteristics of networks. Accordingly, the accurate detection and analysis of the community structure in large-scale IP networks is highly beneficial for their optimization and security management. This paper addresses this issue by proposing a novel community detection method based on the similarity of communication behavior between IP nodes, which is determined by analyzing the communication relationships and frequency of interactions between the nodes in the network. On this basis, the nodes are iteratively added to the community with the highest similarity to form the final community division result. The results of experiments involving both complex public network datasets and real-world IP network datasets demonstrate that the proposed method provides superior community detection performance compared to that of four existing state-of-the-art community detection methods in terms of modularity and normalized mutual information indicators.

VPN traffic identification under HTTPS tunnel is an urgent problem in the field of network security and network management. In the research scenario of TLS encrypted VPN traffic, the existing work mainly focuses on the classification of traffic application types, and there is no specific research on VPN traffic identification under HTTPS tunnel, this makes the existing methods in the VPN traffic identification scenario under HTTPS tunnel subject to the impact of different application type traffic patterns and different network conditions, resulting in reduced identification accuracy and robustness of the model. At the same time, the existing work also lacks the analysis of the TPR and FPR indicators of the model, which results in that the practicability of the existing results cannot be guaranteed. To solve these problems, this paper has confirmed the simulation scenario of VPN traffic identification under HTTPS tunnel. In order to better mine the network behavior characteristics of VPN services, we propose three-dimensional sequence features (TSF) from three aspects: changes in the number of packets, changes in the payload length of packets, and changes in the interaction rules of uplink and downlink packets. Then we convert the features into RGB images to build a CNN based VPN traffic identification framework under HTTPS tunnel. Experiments on the ISCX-TOR dataset show that the Accuracy of the TSF method is 100%, the TPR and F1-Score are more than 99%, and the FPR is only 0.03%. This means that the TSF method has excellent identification accuracy in the VPN traffic identification scenario under the HTTPS tunnel, and can meet the requirements of actual use to a certain extent.