شناسایی برنامه با طبقه‌بندی هوشمند ترافیک شبکه
محورهای موضوعی : فناوری اطلاعات و ارتباطات
1 - پژوهشگاه ارتباطات و فناوری اطلاعات
کلید واژه: طبقه‌بندي ترافيك رمز, معماری عملیاتی, ويژگيهای آماری, شناسایی برنامه, یادگیری ماشین,
چکیده مقاله :
طبقه‌بندی و تحلیل ترافیک، یکی از چالش‌های بزرگ در حوزه داده کاوی و یادگیری ماشین است که نقش مهمی در تأمین امنیت، تضمین کیفیت و مدیریت شبکه دارد. امروزه حجم زیادی از ترافیک انتقالی در بستر شبكه توسط پروتكلهای ارتباطي امن مانند HTTPS رمز می‌شوند. ترافیک رمز، امکان نظارت و تشخیص ترافيک مشکوک و مخرب در زيرساختهاي ارتباطي را (در قبال افزایش امنيت و حريم خصوصي کاربر) کاهش ميدهد و طبقه‌بندی آن بدون رمزگشايي ارتباطات شبكهاي كار دشواري است، چرا که اطلاعات payload از دست ميرود و تنها اطلاعات سرآيند كه بخشي از آن هم در نسخه‌هاي جدید پروتكلهاي ارتباطي شبكه (نظيرTLS1.03) رمز ميشود، قابل دسترس است. از اينرو رويكردهاي قدیمی تحلیل ترافیک مانند روش‌هاي مختلف مبتني بر پورت و Payload کارآمدی خود را از دست داده، و رویکردهای جدید مبتنی بر هوش مصنوعی و یادگیری ماشین در تحلیل ترافیک رمز مورد استفاده قرار می‌گیرند. در این مقاله پس از بررسی روش‌های تحلیل ترافیک، چارچوب معماري عملیاتی برای تحلیل و طبقه‌بندی هوشمند ترافیک طراحی شده است. سپس یک مدل هوشمند با رویکرد شناسایی ترافیک برنامه‌‌ها مبتنی بر معماری پیشنهادی ارائه گردیده و با استفاده از روش‌های یادگیری ماشین روی مجموعه داده ترافیکی Kaggle141 و مجموعه داده محلی مورد ارزیابی قرار گرفته است. نتایج بدست آمده نشان می‌دهد که مدل مبتنی بر جنگل تصادفی، علاوه بر قابلیت تفسیرپذیری بالا در مقایسه با روش‌های یادگیری عمیق، توانسته است دقت بالایی در طبقه‌بندی هوشمند ترافیک (به ترتیب 95% و 97%) نسبت به سایر روش‌های یادگیری ماشین روی مجموعه داده Kaggle141 و ترافیک محلی ارائه دهد.
Traffic classification and analysis is one of the big challenges in the field of data mining and machine learning, which plays an important role in providing security, quality assurance and network management. Today, a large amount of transmission traffic in the network is encrypted by secure communication protocols such as HTTPS. Encrypted traffic reduces the possibility of monitoring and detecting suspicious and malicious traffic in communication infrastructures (instead of increased security and privacy of the user) and its classification is a difficult task without decoding network communications, because the payload information is lost, and only the header information (which is encrypted too in new versions of network communication protocols such as TLS1.03) is accessible. Therefore, the old approaches of traffic analysis, such as various methods based on port and payload, have lost their efficiency, and new approaches based on artificial intelligence and machine learning are used in cryptographic traffic analysis. In this article, after reviewing the traffic analysis methods, an operational architectural framework for intelligent traffic analysis and classification has been designed. Then, an intelligent model for Traffic Classification and Application Identification is presented and evaluated using machine learning methods on Kaggle141. The obtained results show that the random forest model, in addition to high interpretability compared to deep learning methods, has been able to provide high accuracy in traffic classification (95% and 97%) compared to other machine learning methods. Finally, tips and suggestions about using machine learning methods in the operational field of traffic classification have been provided.
[1] D. Gibert, C. Mateu, and J. Planes, “The rise of machine learning for detection and classification of malware: Research developments, trends and challenges,” J. Netw. Comput. Appl., vol. 153, p. 102526, 2020.
[2] J. Pluskal, O. Lichtner, and O. Rysavy, “Traffic Classification and Application Identification in Network Forensics,” 2018, pp. 161–181.
[3] J. Zhao, X. Jing, Z. Yan, W. Pedrycz, Network traffic classification for data fusion: A survey, Information Fusion 72 (2021) 22–47. doi:https://doi.org/10.1016/j.inffus.2021. 02.009
[4] Zihao Wang, Kar-Wai Fok, Vrizlynn L. L. Thing, "Machine Learning for Encrypted Malicious Traffic Detection: Approaches, Datasets and Comparative Study", Computers & Security, Volume 113, 2022.
[5] M. Conti, Q. Q. Li, A. Maragno, and R. Spolaor, “The dark side(-Channel) of Mobile Devices: A survey on network traffic analysis,” IEEE Commun. Surv. Tutorials, 2018.
[6] Z. Liu, R. Wang, N. Japkowicz, Y. Cai, D. Tang, and X. Cai, “Mobile app traffic flow feature extraction and selection for improving classification robustness,” J. Netw. Comput. Appl., 2019.
[7] Eva Papadogiannaki, Sotiris IoannidisSotiris Ioannidis, "A Survey on Encrypted Network Traffic Analysis Applications, Techniques, and Countermeasures", ACM Computing Surveys 54(6):1-35, July 2021.
[8] D. S. Mohamad Amar, "A Survey on Tor Encrypted Traffic Monitoring", International Journal of Advanced Computer Science and Applications 9(8), 2018.
[9] A. Bhatiaa, A. A. Bahugunaa, K. Tiwaria, K. Haribabua, and D. Vishwakarmab, “A Survey on Analyzing Encrypted Network Traffic of Mobile Devices,” Jun. 2020.
[10] Adi Lichy, Ofek Bader, Ran Dubin, Amit Dvir, Chen Hajaj, "When a RF Beats a CNN and GRU, Together - A Comparison of Deep Learning and Classical Machine Learning Approaches for Encrypted Malware Traffic Classification", arXiv:2206.08004v1 [cs.CR] 16 Jun 2022.
[11] T. van Ede, R. Bortolameotti, A. Continella, J. Ren, D. J. Dubois, M. Lindorfer, D. Choffnes, M. van Steen, and A. Peter, “Flowprint: Semi-supervised mobile-app fingerprinting on encrypted network traffic,” in Network and Distributed System Security Symposium (NDSS), vol. 27, 2020.
[12] R.-H. Hwang, M.-C. Peng, C.-W. Huang, P.-C. Lin, and V.-L. Nguyen, “An unsupervised deep learning model for early network traffic anomaly detection,” IEEE Access, vol. 8, pp. 30 387–30 399, 2020.
[13] A. Azab, M. Khasawneh, S. Alrabaee, K.-K. Raymond Choo, M. Sarsour, "Network traffic classification: Techniques, datasets, and challenges", Digital Communications and Networks (2022), doi: https://doi.org/10.1016/j.dcan.2022.09.009.
[14] P. Khandait, N. Hubballi, B. Mazumdar, Efficient keyword matching for deep packet inspection based network traffic classification, in: 2020 International Conference on COMmunication Systems & NETworkS (COMSNETS), IEEE, 2020, pp. 567–570.
[15] S. Rezaei and X. Liu, “Multitask Learning for Network Traffic Classification,” in Proceedings - International Conference on Computer Communications and Networks, ICCCN, 2020.
[16] M. Perera Jayasuriya Kuranage, K. Piamrat, and S. Hamma, “Network Traffic Classification Using Machine Learning for Software Defined Networks,” 2020, pp. 28–39.
[17] M. Lotfollahi, M. J. Siavoshani, R. S. H. Zade, and M. Saberian, “Deep packet: a novel approach for encrypted traffic classification using deep learning,” Soft Comput., vol. 24, no. 3, pp. 1999–2012, 2020.
[18] M. Shafiq, X. Yu, A. A. Laghari, L. Yao, N. K. Karn, and F. Abdessamia, “Network Traffic Classification techniques and comparative analysis using Machine Learning algorithms,” in 2016 2nd IEEE International Conference on Computer and Communications, ICCC 2016 - Proceedings, 2017.
[19] O. Salman, I. H. Elhajj, A. Kayssi, A. Chehab, A review on machine learning–based approaches for internet traffic classification, Annals of Telecommunications 75 (11) (2020) 673–710.
[20] Mohammad Pooya Malek, Shaghayegh Naderi, Hossein Gharaee Garakani, "A Review on Internet Traffic Classification Based on Artificial Intelligence Techniques", International Journal of Information & Communication Technology Research (IJICTR), Vol. 14, N. 2, pp. 1-13, 2022.
[21] Madushi H. Pathmaperuma,Yogachandran Rahulamathavan,Safak Dogan and Ahmet M. Kondoz, "Deep Learning for Encrypted Traffic Classification and Unknown Data Detection", Sensors 2022, 22(19), 7643; https://doi.org/10.3390/s22197643.
[22] "Labeled Network Traffic flows - 141 Applications", Kaggle.com. [Online]. Available: https://www.kaggle.com/jsrojas/ labeled-network-traffic-flows-114-applications. [Accessed: 07- Jan- 2022].
[23] S. Dong, Multi class SVM algorithm with active learning for network traffic classification, Expert Systems with Applications 176 (2021) 114885. doi:https://doi.org/10.1016/j.eswa.2021.114885.
[24] A. A. Afuwape, Y. Xu, J. H. Anajemba, G.Srivastava, Performance evaluation of secured network traffic classification using a machine learning approach, Computer Standards & Interfaces 78 (2021) 103545. doi:https://doi.org/10.1016/j.csi.2021.103545
[25] Bei Lu, Nurbol Luktarhan, Chao Ding and Wenhui Zhang, "ICLSTM: Encrypted Traffic Service Identification Based on Inception-LSTM Neural Network", Symmetry 2021, 13(6), 1080; https://doi.org/10.3390 /sym13061080.
[26] Fathi-Kazerooni, Sina, Yagiz Kaymak, and Roberto Rojas-Cessa. "Identification of user application by an external eavesdropper using machine learning analysis on network traffic." In 2019 IEEE International Conference on Communications Workshops (ICC Works.
[27] Perera, Menuka, Kandaraj Piamrat, and Salima Hamma. "Network Traffic Classification using Machine Learning for Software Defined Networks." In Journées non thématiques GDR-RSD 2020. 2020..
[28] Peng, Lizhi, Bo Yang, and Yuehui Chen. "Effective packet number for early stage internet traffic identification." Neurocomputing 156 (2015): 252-267..
[29] Dong, Yu-ning, Jia-jie Zhao, and Jiong Jin. "Novel feature selection and classification of Internet video traffic based on a hierarchical scheme." Computer Networks 119 (2017): 102-111..
[30] Khatouni, Ali Safari, and Nur Zincir Heywood. "How much training data is enough to move a ML-based classifier to a different network?." Procedia Computer Science 155 (2019): 378-385.
