Special lssues
Table of Content

Evolving Network Traffic Identification Technology

Submission Deadline: 30 January 2023 (closed)

Guest Editors

Prof. Shi Dong, Zhoukou Normal University, China.
Prof. Joarder Kamruzzaman, Federation University Australia, Australia.
Dr. Yongsheng Hao, Nanjing University of Information Science & Technology, China

Summary

Network traffic identification is the key link of network monitoring and plays an important role in network management. From the initial port recognition to deep packet detection, and then to flow recognition based on machine learning. However, the problems of recognition accuracy and real-time on-line processing still exist. In order to reduce unnecessary blocking from security devices such as firewalls, more and more network applications use port reuse technology, which results in the failure of traffic identification methods based on predefined ports. The widely used DPI technique based on pattern matching and the DFI technique based on flow statistical features and machine learning algorithm are difficult to manually label a large number of samples and extract identification features. With the increase of wireless sensor networks and mobile devices, the scale of network traffic is also expanding, which brings new challenges to network traffic identification technology. How to use the new traffic identification technology such as deep learning and pattern recognition to improve the accuracy of traffic identification and reduce its time complexity is still an open problem.

 

Our special issue will serve as a forum to bring together active researchers all over the world to share their recent advances in network traffic identification. Our targets include:

(1) state-of-the-art theories and novel applications in network traffic identification model based on deep learning;(2) novel network traffic identification framework; (3) network traffic identification methods in a specific environment (such as IoT or SDN environment); (4) novel feature selection method with traffic identification; (5) analyses and studies on the behavioral characteristics of network traffic and new traffic identification method based deep learning; (6) traffic identification methods for specific traffic types (for example, for P2P, Skype, DNS) and (7) survey articles reporting the recent progress in traffic identification methods.

 

Potential topics include but are not limited to the following:

•  Innovative network traffic identification models based on deep learning

•  Novel traffic identification framework based on Artificial Intelligence

•  Network traffic identification methods in a specific environment (such as IoT or SDN environment)

•  Traffic identification methods for specific traffic types (for example, for P2P, Skype, DNS) New intelligent optimization methods for traffic identification based on artificial intelligence

•  Novel traffic identification methods based on deep learning

•  How to mine and select more effective network behavior features to identify malicious network traffic

•  New network abnormal traffic detection models based on deep learning/reinforcement learning

•  How to build new traffic identification benchmark data sets

•  Hybrid/ Integrated deep learning model for efficient traffic identification in big data environment

•  Novel feature selection method with traffic identification

•  Encrypted traffic identification in high-speed network environment

•  Real-time traffic identification in high-speed network environment

•  How to address data imbalance problem in building traffic identification models

•  Comprehensive survey articles on recent traffic identification techniques highlighting future challenges


Keywords

Traffic Identification; Network Management; Deep learning; Machine Learning

Published Papers


  • Open Access

    ARTICLE

    An Improved Jump Spider Optimization for Network Traffic Identification Feature Selection

    Hui Xu, Yalin Hu, Weidong Cao, Longjie Han
    CMC-Computers, Materials & Continua, Vol.76, No.3, pp. 3239-3255, 2023, DOI:10.32604/cmc.2023.039227
    (This article belongs to this Special Issue: Evolving Network Traffic Identification Technology)
    Abstract The massive influx of traffic on the Internet has made the composition of web traffic increasingly complex. Traditional port-based or protocol-based network traffic identification methods are no longer suitable for today’s complex and changing networks. Recently, machine learning has been widely applied to network traffic recognition. Still, high-dimensional features and redundant data in network traffic can lead to slow convergence problems and low identification accuracy of network traffic recognition algorithms. Taking advantage of the faster optimization-seeking capability of the jumping spider optimization algorithm (JSOA), this paper proposes a jumping spider optimization algorithm that incorporates the harris hawk optimization (HHO) and… More >

  • Open Access

    ARTICLE

    Self-Awakened Particle Swarm Optimization BN Structure Learning Algorithm Based on Search Space Constraint

    Kun Liu, Peiran Li, Yu Zhang, Jia Ren, Xianyu Wang, Uzair Aslam Bhatti
    CMC-Computers, Materials & Continua, Vol.76, No.3, pp. 3257-3274, 2023, DOI:10.32604/cmc.2023.039430
    (This article belongs to this Special Issue: Evolving Network Traffic Identification Technology)
    Abstract To obtain the optimal Bayesian network (BN) structure, researchers often use the hybrid learning algorithm that combines the constraint-based (CB) method and the score-and-search (SS) method. This hybrid method has the problem that the search efficiency could be improved due to the ample search space. The search process quickly falls into the local optimal solution, unable to obtain the global optimal. Based on this, the Particle Swarm Optimization (PSO) algorithm based on the search space constraint process is proposed. In the first stage, the method uses dynamic adjustment factors to constrain the structure search space and enrich the diversity of… More >

Share Link