Abstract This paper presents a method using neural networks and Markov Decision Process (MDP) to identify the source and class of video streaming services. The paper presents the design and implementation of an end-to-end pipeline for training and classifying a machine learning system that can take in packets collected over a network interface and classify the data stream as belonging to one of five streaming video services: You Tube, You Tube TV, Netflix, Amazon Prime, or HBO.

References

[1] Archanaa R. Athulya V., Rajasundari T., and Kiran M., “A Comparative Performance Analysis on Network Traffic Classification Using Supervised Learning Algorithms,” in Proceedings of 4th International Conference on Advanced Computing and Communication Systems, Coimbatore, pp. 1-5, 2017.

[2] Auld T., Moore A., and Gull S., “Bayesian Neural Networks for Internet Traffic Classification,” IEEE Trans. Neural Networks, vol. 18, no. 1, pp. 223-239, 2007.

[3] Bernaille L. and Teixeira R., “Early Recognition of Encrypted Applications,” in Proceedings of International Conference on Passive and Active Network Measurement, Louvain-la-neuve, pp. 165-175, 2007.

[4] Bonfiglio D., Mellia M., Meo M., Rossi D., and Tofanelli P., “Revealing Skype Traffic: When Randomness Plays with You,” in Proceedings of the Conference on Applications, Technologies, Architectures, and Protocols for Computer Communications, Kyoto, pp. 37-48, 2007.

[5] Erman J., Mahanti A., Arlitt M., and Cohen I., “Semi-Supervised Network Traffic Classification,” ACM SIGMETRICS Performance Evaluation Review, vol. 35, no. 1, 2007.

[6] Erman J. Mahanti A., Arlitt M., and Williamson C., “Identifying and Discriminating between Web and Peer-to-Peer Traffic in the Network Core,” in Proceedings of the 16th International Conference on World Wide WebMay, Banff, pp. 883-892, 2007.

[7] Hubballi N. and Mayank S., “BitCoding: Network Traffic Classification Through Encoded Bit,” IEEE/ACM Transactions on Networking, vol. 26, no. 5, pp. 2334-2346, 2018.

[8] Hofstede R., Čeleda P., Trammell B., Drago I., Sadre R., Sperotto A., and Pras A., “Flow Monitoring Explained: From Packet Capture to Data Analysis with NetFlow and IPFIX,” IEEE Communications Surveys and Tutorials, vol. 16 , no. 4 , pp. 2037-2064, 2014.

[9] Karagiannis T., Konstantina P., and Michalis F., “BLINC: Multilevel Traffic Classification in the Dark,” ACM SIGCOMM Computer Communication Review, vol. 35, no. 4, 2005.

[10] Lotfollahi M., Zade R., Siavoshani M., Saberian M., “Deep Packet: A Novel Approach for Encrypted Traffic Classification Using Deep Learning,” Soft Computing, vol. 24, pp. 1999- 2012, 2020.

[11] “MatConvNet: CNNs for MATLAB” MatconvNet. http://www.vlfeat.org/matconvnet/ Last Visited, 2020.

[12] McGaughey D. Semeniuk T., Smith R., and Knight S., “A Systematic Approach of Feature Selection for Encrypted Network Traffic Classification,” in Proceedings of Annual IEEE International Systems Conference, Vancouver, pp. 1-8, 2018.

[13] Moore A. and Zuev D., “In¬¬ternet Traffic Classification Using Bayesian Analysis Techniques,” ACM SIGMETRICS Performance Evaluation Review (SIGMETRICS, vol. 33, pp. 50-60, 2005.

[14] Nguyen T. and Armitage G., “A Survey of Techniques for Internet Traffic Classification Using Machine Learning,” IEEE Communications Surveys and Tutorials, vol. 10, no. 4, pp. 56-76, 2008.

[15] Orsolic I., Pevec D., Suznjevic M., and Skorin- Kapov L., “You Tube QoE Estimation Based on the Analysis of Encrypted Network Traffic Using Machine Learning,” in Proceedings of Globecom Workshops (GC Wkshps), Washington, 2016.

[16] Ran D., Hadar O., Richman I., Trabelsi O., Dvir A., and Peles O., “Video Quality Representation Classification of Safari Encrypted DASH Streams,” in Proceedings of Digital Media Industry and Academic Forum (DMIAF). Santorini, 2016.

[17] Shafiq M., Yu X., Laghari A., Yao L., Karn N., and Abdessamia F., “Network Traffic Classification Techniques and Comparative Analysis Using Machine Learning Algorithms,” in Proceedings of 2nd IEEE International Conference on Computer and Communications, Chengdu, 2016. 682 The International Arab Journal of Information Technology, Vol. 17, No. 4A, Special Issue 2020

[18] Shaout A. and Crispin B., “Markov Augmented Neural Networks for Streaming Video Classification,” in Proceedings of the IEEE International Arab Conference on Information Technology, Al Ain, pp. 1-7, 2019.

[19] Shaout A., Mysuru D., Raghupathy K., “Vehicle Condition, Driver Behavior Analysis and Data Logging Through CAN Sniffing,” The International Arab Journal of Information Technology, vol. 16, no. 3A, pp. 493-498, 2019.

[20] Wei W., Zhu M., Wang J., and Zeng X., “End- To-End Encrypted Traffic Classification With One-Dimensional Convolution Neural Networks,” in Proceedings of IEEE International Conference on Intelligence and Security Informatics, Beijing, 2017.

[21] Wireshark, Wireshark, www.wireshark.org, Last Visited, 2020.

[22] Zhang J., Xiang Y., Wang Y., Zhou W., Xiang Y., and Guan Y., “Network Traffic Classification Using Correlation Information,” IEEE Transactions on Parallel and Distributed Systems, vol. 24, no. 1, pp. 104-117, 2013. Adnan Shaout is a full professor and a Fulbright Scholar in the Computer Science Department at the Electrical and Computer Engineering Department at the University of Michigan–Dearborn. His current research is in applications of software engineering methods, embedded systems, fuzzy systems, real time systems and AI. Dr. Shaout has published over 260 papers in topics related to Computer Science, Electrical and Computer Engineering fields. Dr. Shaout has obtained his B.S.c, M.S. and Ph.D. in Computer Engineering from Syracuse University, Syracuse, NY, in 1982, 1983, 1987, respectively. Brennan Crispin has an MS degree in Software Engineering from the University of Michigan – Dearborn. He is currently working as a Software Engineer at Deepfield- Ann Arbor, MI.