In recent years, with the rapid development of Internet services in all walks of life, a large number of malicious acts such as network attacks, data leakage, and information theft have become major challenges for network security. Due to the difficulty of malicious traffic collection and labeling, the distribution of various samples in the existing dataset is seriously imbalanced, resulting in low accuracy of malicious traffic classification based on machine learning and deep learning, and poor model generalization ability. In this paper, a feature image representation method and Adversarial Generative Network with Filter (Filter-GAN) are proposed to solve these problems. First, the feature image representation method divides the original session traffic into three parts. The Markov matrix is extracted from each part to form a three-channel feature image. This method can transform the original session traffic format into a uniform-length matrix and fully characterize the network traffic. Then, Filter-GAN uses the feature images to generate few attack samples. Compared with general methods, Filter-GAN can generate more efficient samples. Experiments were conducted on public datasets. The results show that the feature image representation method can effectively characterize the original session traffic. When the number of samples is sufficient, the classification accuracy can reach 99%. Compared with unbalanced datasets, Filter-GAN has significantly improved the recognition accuracy of small-sample datasets, with a maximum improvement of 6%.

Desktop as a Service (DaaS) provides users with flexible, customizable and highly secure cloud based virtual desktop access. As the major carrier of execution results in DaaS, screen updates play an important role in users’ quality of experience. In order to bring users the same feelings like manipulating a local device, timeliness and reliability should be balanced. However, a timely but unreliable transmission scheme (i.e. UDP) or a completely reliable transmission scheme (i.e. TCP) is inappropriate for such a transmission scenario, especially under a high-loss network. In this paper, we propose a Prediction and Network Coding based Transmission Scheme (PNCTS) for efficient screen updates delivery in DaaS. As an end-to-end partially reliable transmission scheme, it prioritizes different data obtained by partitioning screen updates and employs network coding and TFRC (TCP Friendly Rate Control) to compensate for data loss and adjust the sending rate of screen updates, respectively. To reduce the overhead of network coding, PNCTS uses a Hidden Markov Model to predict the reliability level of network and makes different encoding strategies for the data with different priorities. Simulation results show that PNCTS can improve display quality and instantaneous goodput effectively while maintaining end-to-end delay and jitter at a relatively low level under the static and time-varying network conditions.

No abstract