Effective Media Traffic Classification Using Deep Learning

Traffic classification (TC) is very important as it can provide useful information which can be used in the flexible management of the network. However, TC has become more and more complicated because of the emergence of various network applications and techniques. In this paper, we apply deep learning based method to the classification of four different kinds of media traffic, i.e., audio, picture, text and video. We collect traffic data from the real network environment. Multilayer Perceptron (MLP) and Convolutional Neural Network (CNN) based traffic classification methods are designed to accurately classify the target traffic into different categories. We found that MLP has very good performance in most scenarios. Moreover, specific architecture can reduce the training time of the neural network in the classification.

[1]  T. V. Lakshman,et al.  Variable-Stride Multi-Pattern Matching For Scalable Deep Packet Inspection , 2009, IEEE INFOCOM 2009.

[2]  Dario Rossi,et al.  KISS: Stochastic Packet Inspection Classifier for UDP Traffic , 2010, IEEE/ACM Transactions on Networking.

[3]  Guodong Li,et al.  DFC: Towards Effective Feedback Flow Management for Datacenters , 2010, 2010 Ninth International Conference on Grid and Cloud Computing.

[4]  Shijie Sun,et al.  MN-SLA: a modular networking SLA framework for cloud management system , 2018, Tsinghua Science and Technology.

[5]  Julong Lan,et al.  QoS-aware Traffic Classification Architecture Using Machine Learning and Deep Packet Inspection in SDNs , 2018 .

[6]  Seungjoon Lee,et al.  Network function virtualization: Challenges and opportunities for innovations , 2015, IEEE Communications Magazine.

[7]  Amin Vahdat,et al.  BwE: Flexible, Hierarchical Bandwidth Allocation for WAN Distributed Computing , 2015, Comput. Commun. Rev..

[8]  Jun Li,et al.  Multi-core HTB for bandwidth sharing , 2018, ANCS.

[9]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[10]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[11]  Grenville Armitage,et al.  Synthetic sub-flow pairs for timely and stable IP traffic identification , 2006 .

[12]  Gunjan Tank,et al.  Software-Defined Networking-The New Norm for Networks , 2012 .

[13]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[14]  Mahdi Jafari Siavoshani,et al.  Deep packet: a novel approach for encrypted traffic classification using deep learning , 2017, Soft Computing.

[15]  Baohua Yang,et al.  SMILER: Towards Practical Online Traffic Classification , 2011, 2011 ACM/IEEE Seventh Symposium on Architectures for Networking and Communications Systems.

[16]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[17]  Nick McKeown,et al.  OpenFlow: enabling innovation in campus networks , 2008, CCRV.

[18]  Zhi Liu,et al.  Towards efficient load distribution in big data cloud , 2015, 2015 International Conference on Computing, Networking and Communications (ICNC).

[19]  Shie Mannor,et al.  A Tutorial on the Cross-Entropy Method , 2005, Ann. Oper. Res..

[20]  Muhammad Shafiq,et al.  Effective Packet Number for 5G IM WeChat Application at Early Stage Traffic Classification , 2017, Mob. Inf. Syst..

[21]  Andrew W. Moore,et al.  Internet traffic classification using bayesian analysis techniques , 2005, SIGMETRICS '05.

[22]  S. Mohamed,et al.  Statistical Normalization and Back Propagation for Classification , 2022 .

[23]  Hamid H. Jebur,et al.  Machine Learning Techniques for Anomaly Detection: An Overview , 2013 .

[24]  Kurt Hornik,et al.  FEED FORWARD NETWORKS ARE UNIVERSAL APPROXIMATORS , 1989 .

[25]  Andrew W. Moore,et al.  Bayesian Neural Networks for Internet Traffic Classification , 2007, IEEE Transactions on Neural Networks.

[26]  David Walker,et al.  SNAP: Stateful Network-Wide Abstractions for Packet Processing , 2015, SIGCOMM.

[27]  Konstantina Papagiannaki,et al.  Toward the Accurate Identification of Network Applications , 2005, PAM.

[28]  Yibo Xue,et al.  Towards time-varying classification based on traffic pattern , 2014, 2014 IEEE Conference on Communications and Network Security.

[29]  Michalis Faloutsos,et al.  File-sharing in the Internet: A characterization of P2P traffic in the backbone , 2003 .

[30]  B. Frey,et al.  Predicting the sequence specificities of DNA- and RNA-binding proteins by deep learning , 2015, Nature Biotechnology.

[31]  B. Karp,et al.  Autograph: Toward Automated, Distributed Worm Signature Detection , 2004, USENIX Security Symposium.

[32]  Cícero Nogueira dos Santos,et al.  Deep Convolutional Neural Networks for Sentiment Analysis of Short Texts , 2014, COLING.

[33]  Mohammad Reza Parsaei,et al.  Network Traffic Classification using Machine Learning Techniques over Software Defined Networks , 2017 .

[34]  K. P. Soman,et al.  Deep Learning for Network Flow Analysis and Malware Classification , 2017, SSCC.

[35]  Zhenlong Yuan,et al.  Harvesting unique characteristics in packet sequences for effective application classification , 2013, 2013 IEEE Conference on Communications and Network Security (CNS).

[36]  Honglak Lee,et al.  Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations , 2009, ICML '09.

[37]  Antonio Pescapè,et al.  Issues and future directions in traffic classification , 2012, IEEE Network.

[38]  Min Luo,et al.  A Framework for QoS-aware Traffic Classification Using Semi-supervised Machine Learning in SDNs , 2016, 2016 IEEE International Conference on Services Computing (SCC).

[39]  Eduardo Rocha,et al.  A Survey of Payload-Based Traffic Classification Approaches , 2014, IEEE Communications Surveys & Tutorials.

[40]  Carey L. Williamson,et al.  A Longitudinal Study of P2P Traffic Classification , 2006, 14th IEEE International Symposium on Modeling, Analysis, and Simulation.

[41]  A. Santhakumaran,et al.  Statistical Normalization and Back Propagationfor Classification , 2011 .

[42]  Pan Wang,et al.  Datanet: Deep Learning Based Encrypted Network Traffic Classification in SDN Home Gateway , 2018, IEEE Access.

[43]  Baohua Yang,et al.  Emilie: Enhance the power of traffic identification , 2014, 2014 International Conference on Computing, Networking and Communications (ICNC).

[44]  Jun Li,et al.  PPP: Towards Parallel Protocol Parsing , 2014, China Communications.