ارائه راهکاری نوین برای طبقه‌بندی ترافیک رمزنگاری‌شده با بهره‌گیری از یادگیری عمیق

نوع مقاله : مقاله پژوهشی

نویسندگان

1 کارشناسی ارشد گروه مهندسی کامپیوتر، دانشکده فناوری و مهندسی، دانشگاه مازندران، بابلسر، ایران

2 استادیار گروه مهندسی کامپیوتر، دانشکده فناوری و مهندسی، دانشگاه مازندران، بابلسر، ایران

10.22034/abmir.2025.22525.1084

چکیده

تحلیل ترافیک شبکه یکی از ارکان اساسی در بهبود امنیت و مدیریت کارآمد شبکه‌های کامپیوتری است. با توجه به گسترش روزافزون شبکه‌های کامپیوتری و پیچیدگی‌های ترافیک موجود در آن‌ها، شناسایی دقیق و سریع انواع ترافیک ازجمله ترافیک رمزنگاری‌شده، از اهمیت ویژه‌ای برخوردار است. در این راستا، استفاده از تکنیک‌های یادگیری ماشین می‌تواند ابزار قدرتمندی برای تحلیل و شناسایی دقیق الگوهای ترافیکی باشد. این مقاله به بررسی روش‌های پیشرفته شناسایی ترافیک در شبکه‌های کامپیوتری با بهره‌گیری از تکنیک‌های یادگیری ماشین پرداخته است. هدف اصلی این تحقیق، توسعه مدلی کارآمد و دقیق برای شناسایی و طبقه‌بندی انواع مختلف ترافیک شبکه، به‌ویژه ترافیک رمزنگاری‌شده، است. در این راستا، از مدل یادگیری عمیق VGG16 استفاده‌شده است. این مدل به دلیل ساختار لایه‌ای عمیق و توانایی تحلیل داده‌های حجیم، عملکرد برجسته‌ای در شناسایی الگوهای پیچیده ترافیک شبکه ارائه داده است. VGG16 قادر است با دقت بالا، انواع مختلف ترافیک شبکه را شناسایی و طبقه‌بندی کند، که این امر منجر به بهبود مدیریت ترافیک در شبکه می‌شود. در سناریوهای بررسی‌شده در این تحقیق، این مدل توانست دقت 99 درصدی را در شناسایی ترافیک رمزنگاری‌شده به‌دست آورد.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

A Novel Approach for Encrypted Traffic Classification Using Deep Learning

نویسندگان [English]

  • Pooya Rabiei Dolatabadi 1
  • Mostafa Bastam 2
  • Khadijeh Aghajani 2
1 M.Sc Computer Engineering, Faculty of Technology and Engineering, University of Mazandaran, Babolsar, Iran
2 Assistant Professor Department of Computer Engineering, Faculty of Technology and Engineering, University of Mazandaran, Babolsar, Iran
چکیده [English]

Network traffic analysis is a fundamental pillar in enhancing the security and efficient management of computer networks. Given the rapid growth of computer networks and the increasing complexity of their traffic, accurate and fast identification of various types of traffic, including encrypted traffic, has become crucial. In this context, the use of machine learning techniques offers a powerful tool for analyzing and accurately identifying traffic patterns. This paper examines advanced methods for traffic identification in computer networks using machine learning techniques. The primary goal of this research is to develop an efficient and accurate model for identifying and classifying various types of network traffic, particularly encrypted traffic. To achieve this, the deep learning model VGG16 was utilized. Due to its deep layered architecture and capability to analyze large volumes of data, VGG16 demonstrated outstanding performance in identifying complex network traffic patterns. It can accurately detect and classify different types of network traffic, thereby improving traffic management within networks. In the scenarios evaluated in this study, the model achieved a remarkable accuracy of 99% in identifying encrypted traffic.

کلیدواژه‌ها [English]

  • Deep Learning
  • Network Traffic Analysis
  • Encrypted Traffic
  • VGG16 model
  • Network Traffic Management

مراجع

[1]  A. R. Bahlali, A. Bachir, and A. Cheriet, “Malicious encrypted network traffic detection using deep auto-encoder with a custom reconstruction loss,” in 2023 International Symposium on Networks, Computers and Communications (ISNCC), 2023.
[2]     J. Cao et al., “An improved network traffic classification model based on a support vector machine,” Symmetry, vol. 12, no. 2, p. 301, 2020, doi: 10.3390/sym12020301.
[3]     P. Choorod, T. J. Bauer, and A. Aßmuth, “Distinguishing Tor from other encrypted network traffic through character analysis,” arXiv preprint arXiv:2405.09412, 2024.
[4]     Y. Cui and A. Li, “Research on network encrypted traffic detection technology based on CNN + LSTM,” in 2024 2nd International Conference on Signal Processing and Intelligent Computing (SPIC), 2024.
[5]     L. Deri and F. Fusco, “Using deep packet inspection in cybertraffic analysis,” in 2021 IEEE International Conference on Cyber Security and Resilience (CSR), 2021, doi: 10.1109/CSR51186.2021.9527976.
[6]     C. Hardegen et al., “Predicting network flow characteristics using deep learning and real-world network traffic,” IEEE Trans. Netw. Serv. Manage., vol. 17, no. 4, pp. 2662–2676, 2020.
[7]     E. Horowicz, T. Shapira, and Y. Shavitt, “Self-supervised traffic classification: Flow embedding and few-shot solutions,” IEEE Trans. Netw. Serv. Manage., 2024, doi: 10.1109/TNSM.2024.3366848.
[8]     E. Horowicz, T. Shapira, and Y. Shavitt, “A few shots traffic classification with mini-flowpic augmentations,” in Proc. 22nd ACM Internet Measurement Conference, 2022, doi: 10.1145/3517745.3561436.
[9]     S. Li et al., “Network traffic prediction based on the feature of newly-generated network flows,” in 2022 IFIP Networking Conference (IFIP Networking), 2022.
[10] X. Liu et al., “Mal‑lightDet: A light method to detect malicious encrypted traffic based on machine learning,” in Proc. 4th Int. Conf. Control, Robotics and Intelligent System, 2023, doi: 10.1145/3622896.3622907.
[11] Y. Liu et al., “Encrypted malicious traffic detection based on graph convolutional network and temporal dissection,” in 2024 27th Int. Conf. Comput. Supported Cooperative Work in Design (CSCWD), 2024.
[12] M. Lotfollahi et al., “Deep packet: A novel approach for encrypted traffic classification using deep learning,” Soft Comput., vol. 24, no. 3, pp. 1999–2012, 2020, doi: 10.1007/s00500‑019‑04030‑2.
[13] S. Mascarenhas and M. Agarwal, “A comparison between VGG16, VGG19 and ResNet50 architecture frameworks for image classification,” in 2021 Int. Conf. Disruptive Technol. for Multi-Disciplinary Res. and Appl. (CENTCON), 2021.
[14] S. Rezaei, B. Kroencke, and X. Liu, “Large-scale mobile app identification using deep learning,” IEEE Access, vol. 8, pp. 348–362, 2019.
[15] T. Shapira and Y. Shavitt, “FlowPic: A generic representation for encrypted traffic classification and applications identification,” IEEE Trans. Netw. Serv. Manage., vol. 18, no. 2, pp. 1218–1232, 2021, doi: 10.1109/TNSM.2021.3071441.
[16] M. Shen et al., “Machine learning-powered encrypted network traffic analysis: A comprehensive survey,” IEEE Commun. Surveys Tuts., vol. 25, no. 1, pp. 791–824, 2022, doi: 10.1109/COMST.2022.3208196.
[17] G. Siracusano et al., “Re-architecting traffic analysis with neural network interface cards,” in Proc. 19th USENIX Symp. Netw. Syst. Design and Implementation (NSDI 22), 2022.
[18] L. Swarup, “Encrypted traffic analysis for malware detection using deep learning,” in 2023 IEEE Int. Conf. ICT in Business Industry & Government (ICTBIG), 2023.
[19] V. Tong et al., “A novel QUIC traffic classifier based on convolutional neural networks,” in 2018 IEEE Global Communications Conference (GLOBECOM), 2018.
[20] A. Finamore, C. Wang, J. Krolikowski, J. M. Navarro, F. Chen, and D. Rossi, “Curated UCDAVIS19 dataset for replication: Contrastive learning and data augmentation in traffic classification using a Flowpic input representation,” Figshare, Oct. 2023. [Online]. Available: https://doi.org/10.6084/m9.figshare.23538141.
[21] J. Xing and C. Wu, “Detecting anomalies in encrypted traffic via deep dictionary learning,” in IEEE INFOCOM 2020–IEEE Conf. Comput. Commun. Workshops (INFOCOM WKSHPS), 2020.
[22] X. Yang, N. Angkawisittpan, and X. Feng, “Analysis of an enhanced random forest algorithm for identifying encrypted network traffic,” EUREKA: Physics and Engineering, no. 5, pp. 201–212, 2024, doi: 10.21303/2461‑4262.2024.003372.
[23] N. Zhou, “Image recognition in depth: Comparative study of CNN and pre‑trained VGG16 architecture for classification tasks,” in Proc. Second Int. Conf. Physics, Photonics, and Optical Engineering (ICPPOE 2023), 2024, doi: 10.1117/12.3026829.
[24] Y. Zion, P. Aharon, R. Dubin, A. Dvir, and C. Hajaj, “Enhancing encrypted internet traffic classification through advanced data augmentation techniques,” arXiv preprint arXiv:2407.16539, 2024.
پژوهش های نظری و کاربردی هوش ماشینی
دوره 2، شماره 2
اسفند 1403
صفحه 17-29

فایل ها

هم رسانی

ارجاع به این مقاله

آمار