skip to main content
10.1145/3405837.3411369acmconferencesArticle/Chapter ViewAbstractPublication PagescommConference Proceedingsconference-collections
poster

Traffic classification using deep learning: being highly accurate is not enough

Published: 14 September 2021 Publication History

Abstract

As Deep Learning (DL) algorithms have rapidly become a methodology of choice in various domains, they have recently entered also the field of the Internet traffic classification, successfully demonstrating impressive results. Most of the research work up to this point has focused on improving the accuracy of classification systems, yet there has been little attempt to provide (i) systematic comparison of the various DL algorithms used and (ii) analysis on where the higher accuracy come from, particularly when comparing with the traditional machine learning algorithms like C4.5. To fill this gap, we conduct experiments with four DL algorithms proposed for traffic classification, including CNN, LSTM, Stacked Auto-Encoder (SAE), and Hierarchical Attention Networks (HAN). Further, we propose to leverage and visualize hierarchical attention layers to highlight which parts of the traffic packet traces were most informative for accurate classification, which provides hints about why (and how) DL algorithms achieve the state-of-the-art level high accuracy. We view this paper as the first step towards answering the aforementioned "why" question, which is critical in understanding the real benefit and contribution of deep learning to the field of the Internet traffic classification, and advancing its state-of-the-art.

References

[1]
W Wang et al. 2017. Malware traffic classification using convolutional neural network for representation learning. In ICOIN.
[2]
Y Lim et al. 2010. Internet traffic classification demystified: on the sources of the discriminative power. In CoNEXT.
[3]
Z Yang et al. 2016. Hierarchical attention networks for document classification. In NAACL.
[4]
CTU University. 2016. The Stratosphere IPS Project Dataset. https://stratosphereips.org/category/dataset.html (2016).

Cited By

View all
  • (2024)No Pictures, Please: Using eXplainable Artificial Intelligence to Demystify CNNs for Encrypted Network Packet ClassificationApplied Sciences10.3390/app1413546614:13(5466)Online publication date: 24-Jun-2024
  • (2024)SHTree: A Structural Encrypted Traffic Fingerprint Generation Method for Multiple Classification Tasks2024 IEEE Symposium on Computers and Communications (ISCC)10.1109/ISCC61673.2024.10733622(1-7)Online publication date: 26-Jun-2024
  • (2023)A Multimodal Network Security Framework for Healthcare Based on Deep LearningComputational Intelligence and Neuroscience10.1155/2023/90413552023:1Online publication date: 20-Feb-2023

Index Terms

  1. Traffic classification using deep learning: being highly accurate is not enough

      Recommendations

      Comments

      Information & Contributors

      Information

      Published In

      cover image ACM Conferences
      SIGCOMM '20: Proceedings of the SIGCOMM '20 Poster and Demo Sessions
      August 2020
      96 pages
      ISBN:9781450380485
      DOI:10.1145/3405837
      Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the Owner/Author.

      Sponsors

      Publisher

      Association for Computing Machinery

      New York, NY, United States

      Publication History

      Published: 14 September 2021

      Check for updates

      Author Tags

      1. deep learning
      2. eXplainable AI
      3. traffic classification

      Qualifiers

      • Poster

      Funding Sources

      • Korean government (MSIT)

      Conference

      SIGCOMM '20
      Sponsor:

      Acceptance Rates

      Overall Acceptance Rate 92 of 158 submissions, 58%

      Contributors

      Other Metrics

      Bibliometrics & Citations

      Bibliometrics

      Article Metrics

      • Downloads (Last 12 months)46
      • Downloads (Last 6 weeks)1
      Reflects downloads up to 16 Jan 2025

      Other Metrics

      Citations

      Cited By

      View all
      • (2024)No Pictures, Please: Using eXplainable Artificial Intelligence to Demystify CNNs for Encrypted Network Packet ClassificationApplied Sciences10.3390/app1413546614:13(5466)Online publication date: 24-Jun-2024
      • (2024)SHTree: A Structural Encrypted Traffic Fingerprint Generation Method for Multiple Classification Tasks2024 IEEE Symposium on Computers and Communications (ISCC)10.1109/ISCC61673.2024.10733622(1-7)Online publication date: 26-Jun-2024
      • (2023)A Multimodal Network Security Framework for Healthcare Based on Deep LearningComputational Intelligence and Neuroscience10.1155/2023/90413552023:1Online publication date: 20-Feb-2023

      View Options

      Login options

      View options

      PDF

      View or Download as a PDF file.

      PDF

      eReader

      View online with eReader.

      eReader

      Media

      Figures

      Other

      Tables

      Share

      Share

      Share this Publication link

      Share on social media