research-article

Open access

Explainable Mobile Traffic Classification: the Case of Incremental Learning

Authors:

Alfredo Nascita,

Francesco Cerasuolo,

Giuseppe Aceto,

Domenico Ciuonzo,

Valerio Persico,

Antonio PescapéAuthors Info & Claims

SAFE '23: Proceedings of the 2023 on Explainable and Safety Bounded, Fidelitous, Machine Learning for Networking

Pages 25 - 31

https://doi.org/10.1145/3630050.3630178

Published: 05 December 2023 Publication History

Abstract

The surge in mobile network usage has contributed to the adoption of Deep Learning (DL) techniques for Traffic Classification (TC) to ensure efficient network management. However, DL-based classifiers still face challenges due to the frequent release of new apps (making them outdated) and the lack of interpretability (limiting their adoption). In this regard, Class Incremental Learning and eXplainable Artificial Intelligence have emerged as fundamental methodological tools. This work aims at reducing the gap between the DL models' performance and their interpretability in the TC domain. In this study, we examine from different perspectives the differences between classifiers when trained from scratch and incrementally. Using Deep SHAP, we derive global explanations to emphasize disparities in input importance. We comprehensively analyze base classifiers' behavior to understand the starting point of the incremental process and examine updated models to uncover architectures' features resulting from the incremental training.

The analysis is based on MIRAGE19, an open dataset focused on mobile app traffic.

References

[1]

Giuseppe Aceto, Domenico Ciuonzo, Antonio Montieri, Valerio Persico, and Antonio Pescapé. 2019. MIRAGE: Mobile-app Traffic Capture and Ground-truth Creation. In 2019 4th International Conference on Computing, Communications and Security (ICCCS). 1--8. https://doi.org/10.1109/CCCS.2019.8888137

[2]

Giuseppe Aceto, Domenico Ciuonzo, Antonio Montieri, and Antonio Pescapè. 2019. MIMETIC: Mobile encrypted traffic classification using multimodal deep learning. Elsevier Computer Networks 165 (2019), 106944. https://doi.org/10.1016/j.comnet.2019.106944

Digital Library

[3]

Giuseppe Aceto, Domenico Ciuonzo, Antonio Montieri, and Antonio Pescapé. 2019. Mobile encrypted traffic classification using deep learning: Experimental evaluation, lessons learned, and challenges. IEEE Transactions on Network and Service Management 16, 2 (2019), 445--458. https://doi.org/10.1109/TNSM.2019.2899085

[4]

Cedric Beliard, Alessandro Finamore, and Dario Rossi. 2020. Opening the deep Pandora box: Explainable traffic classification. In IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS). IEEE, 1292--1293. https://doi.org/10.1109/INFOCOMWKSHPS50562.2020.9162704

[5]

Giampaolo Bovenzi, Alfredo Nascita, Lixuan Yang, Alessandro Finamore, Giuseppe Aceto, Domenico Ciuonzo, Antonio Pescapé, and Dario Rossi. 2023. Benchmarking Class Incremental Learning in Deep Learning Traffic Classification. IEEE Transactions on Network and Service Management (2023), 1--1. https://doi.org/10.1109/TNSM.2023.3287430

Digital Library

[6]

Giampaolo Bovenzi, Lixuan Yang, Alessandro Finamore, Giuseppe Aceto, Domenico Ciuonzo, Antonio Pescape, and Dario Rossi. 2021. A first look at class incremental learning in deep learning mobile traffic classification. arXiv preprint arXiv:2107.04464 (2021). https://doi.org/10.48550/arXiv.2107.04464

[7]

Yige Chen, Tianning Zang, Yongzheng Zhang, Yuan Zhou, Linshu Ouyang, and Peng Yang. 2021. Incremental Learning for Mobile Encrypted Traffic Classification. In IEEE International Conference on Communications (ICC). IEEE, 1--6. https://doi.org/10.1109/ICC42927.2021.9500619

[8]

Ericsson. 2023. Ericsson Mobility Report. https://www.ericsson.com/49dd9d/assets/local/reports-papers/mobility-report/documents/2023/ericssonmobility-report-june-2023.pdf.

[9]

Kevin Fauvel, Fuxing Chen, and Dario Rossi. 2023. A Lightweight, Efficient and Explainable-by-Design Convolutional Neural Network for Internet Traffic Classification. In Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (Long Beach, CA, USA) (KDD '23). Association for Computing Machinery, 4013--4023. https://doi.org/10.1145/3580305.3599762

Digital Library

[10]

Luis Garcia, Genevieve Bartlett, Srivatsan Ravi, Harun Ibrahim, Wes Hardaker, and Erik Kline. 2022. Explaining Deep Learning Models for Per-packet Encrypted Network Traffic Classification. In IEEE International Symposium on Measurements & Networking (M&N). IEEE, 1--6. https://doi.org/10.1109/MN55117.2022.9887744

[11]

Ian J Goodfellow, Mehdi Mirza, Da Xiao, Aaron Courville, and Yoshua Bengio. 2013. An empirical investigation of catastrophic forgetting in gradient-based neural networks. arXiv preprint arXiv:1312.6211 (2013). https://doi.org/10.48550/arXiv.1312.6211

[12]

Dan Hendrycks and Kevin Gimpel. 2016. Abaseline for detecting misclassified and out-of-distribution examples in neural networks. arXiv preprint arXiv:1610.02136 (2016). https://doi.org/10.48550/arXiv.1610.02136

[13]

Steven Jorgensen, John Holodnak, Jensen Dempsey, Karla de Souza, Ananditha Raghunath, Vernon Rivet, Noah DeMoes, Andrés Alejos, and Allan Wollaber. 2023. Extensible Machine Learning for Encrypted Network Traffic Application Labeling via Uncertainty Quantification. IEEE Transactions on Artificial Intelligence (2023), 1--15. https://doi.org/10.1109/TAI.2023.3244168

[14]

Minsoo Kang, Jaeyoo Park, and Bohyung Han. 2022. Class-incremental learning by knowledge distillation with adaptive feature consolidation. In Proc. of the IEEE/CVF conference on computer vision and pattern recognition. IEEE, 16071--16080. https://doi.org/10.1109/CVPR52688.2022.01560

[15]

Scott M Lundberg and Su-In Lee. 2017. A Unified Approach to Interpreting Model Predictions. In Advances in Neural Information Processing Systems, I. Guyon, U. Von Luxburg, S. Bengio, H.Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc., 4765--4774. https://proceedings.neurips.cc/paper_files/paper/2017/file/8a20a8621978632d76c43dfd28b67767-Paper.pdf

[16]

Xiuli Ma, Wenbin Zhu, Jieling Wei, Yanliang Jin, Dongsheng Gu, and Rui Wang. 2023. EETC: An extended encrypted traffic classification algorithm based on variant ResNet network. Elsevier Computers & Security 128 (2023), 103175. https://doi.org/10.1016/j.cose.2023.103175

Digital Library

[17]

Marc Masana, Xialei Liu, Bartłomiej Twardowski, Mikel Menta, Andrew D. Bagdanov, and Joost van de Weijer. 2023. Class-Incremental Learning: Survey and Performance Evaluation on Image Classification. IEEE Transactions on Pattern Analysis and Machine Intelligence 45, 5 (2023), 5513--5533. https://doi.org/10.1109/TPAMI.2022.3213473

Digital Library

[18]

Alfredo Nascita, Antonio Montieri, Giuseppe Aceto, Domenico Ciuonzo, Valerio Persico, and Antonio Pescapé. 2021. XAI meets mobile traffic classification: Understanding and improving multimodal deep learning architectures. IEEE Transactions on Network and Service Management 18, 4 (2021), 4225--4246. https://doi.org/10.1109/TNSM.2021.3098157

[19]

Alfredo Nascita, Antonio Montieri, Giuseppe Aceto, Domenico Ciuonzo, Valerio Persico, and Antonio Pescapé. 2023. Improving Performance, Reliability, and Feasibility in Multimodal Multitask Traffic Classification with XAI. IEEE Transactions on Network and Service Management 20, 2 (2023), 1267--1289. https://doi.org/10.1109/TNSM.2023.3246794

Digital Library

[20]

Dawid Rymarczyk, Joost van de Weijer, Bartosz Zieliński, and Bartlomiej Twardowski. 2023. ICICLE: Interpretable Class Incremental Continual Learning. In Proceedings of the IEEE/CVF International Conference on Computer Vision. IEEE, 1887--1898. https://doi.org/10.48550/arXiv.2303.07811

[21]

Lloyd S Shapley. 1953. A value for n-person games. Contributions to the Theory of Games 2, 28 (1953), 307--317.

[22]

Zhuoxue Song, Ziming Zhao, Fan Zhang, Gang Xiong, Guang Cheng, Xinjie Zhao, Shize Guo, and Binbin Chen. 2023. I2 RNN: An Incremental and Interpretable Recurrent Neural Network for Encrypted Traffic Classification. IEEE Transactions on Dependable and Secure Computing (2023), 1--14. https://doi.org/10.1109/TDSC.2023.3245411

[23]

Laurens van der Maaten and Geoffrey Hinton. 2008. Visualizing high-dimensional data using t-SNE. J Mach Learn Res 9, 2579--2605 (2008), 9.

[24]

Xin Wang, Shuhui Chen, and Jinshu Su. 2020. Real network traffic collection and deep learning for mobile app identification. Wireless Communications and Mobile Computing 2020 (2020), 1--14. https://doi.org/10.1155/2020/4707909

[25]

Yue Wu, Yinpeng Chen, Lijuan Wang, Yuancheng Ye, Zicheng Liu, Yandong Guo, and Yun Fu. 2019. Large scale incremental learning. In Proc. IEEE/CVF CVPR. 374--382. https://doi.org/10.1109/CVPR.2019.00046

[26]

Zheng Wu, Yu ning Dong, Xiaohui Qiu, and Jiong Jin. 2022. Online multimedia traffic classification from the QoS perspective using deep learning. Computer Networks 204 (2022), 108716. https://doi.org/10.1016/j.comnet.2021.108716

Digital Library

[27]

Wenbin Zhu, Xiuli Ma, Yanliang Jin, and Rui Wang. 2023. ILETC: Incremental learning for encrypted traffic classification using generative replay and exemplar. Elsevier Computer Networks 224 (2023), 109602. https://doi.org/10.1016/j.comnet.2023.109602

Digital Library

Cited By

Goścień R(2024)Traffic Prediction- and Explainable Artificial Intelligence-Based Dynamic Routing in Software-Defined Elastic Optical Networks2024 IFIP Networking Conference (IFIP Networking)10.23919/IFIPNetworking62109.2024.10619798(750-756)Online publication date: 3-Jun-2024
https://doi.org/10.23919/IFIPNetworking62109.2024.10619798
Pérez PFiandrino CFiore MWidmer J(2024)An In-Depth Analysis of Advanced Time Series Forecasting Models for the Open RANIEEE INFOCOM 2024 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)10.1109/INFOCOMWKSHPS61880.2024.10620742(1-6)Online publication date: 20-May-2024
https://doi.org/10.1109/INFOCOMWKSHPS61880.2024.10620742

Index Terms

Explainable Mobile Traffic Classification: the Case of Incremental Learning
1. Networks
  1. Network services
    1. Network monitoring

Recommendations

Multi-classification approaches for classifying mobile app traffic

The growing usage of smartphones in everyday life is deeply (and rapidly) changing the nature of traffic traversing home and enterprise networks, and the Internet. Different tools and middleboxes, such as performance enhancement proxies, network ...
Learning for accurate classification of real-time traffic
CoNEXT '06: Proceedings of the 2006 ACM CoNEXT conference

Accurate network traffic classification is an important task. We intend to develop an intelligent classification system by learning the types of service inside a network flow using machine learning techniques. Previous work used Bayesian methods for ...
Classification of Correlated Internet Traffic Flows
TRUSTCOM '12: Proceedings of the 2012 IEEE 11th International Conference on Trust, Security and Privacy in Computing and Communications

A critical problem for Internet traffic classification is how to obtain a high-performance statistical feature based classifier using a small set of training data. The solutions to this problem are essential to deal with the encrypted applications and ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Conferences

SAFE '23: Proceedings of the 2023 on Explainable and Safety Bounded, Fidelitous, Machine Learning for Networking

December 2023

37 pages

ISBN:9798400704499

DOI:10.1145/3630050

Program Chairs:
Kamal Singh
University St-Etienne, France
,
Abbas Bradai
University of Poitiers, France
,
Pham Tran Anh Quang
Huawei Technologies, France
,
Antonio Pescape
University of Napoli Federico II, Italy
,
Claudio Fiandrino
IMDEA Networks Institute, Madrid, Spain

Copyright © 2023 Owner/Author.

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike International 4.0 License.

Sponsors

SIGCOMM: ACM Special Interest Group on Data Communication

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 05 December 2023

Check for updates

Author Tags

Qualifiers

Research-article

Conference

CoNEXT 2023

Sponsor:

SIGCOMM

CoNEXT 2023: The 19th International Conference on emerging Networking EXperiments and Technologies

December 8, 2023

Paris, France

Upcoming Conference

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
217
Total Downloads

Downloads (Last 12 months)217
Downloads (Last 6 weeks)25

Reflects downloads up to 19 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

Goścień R(2024)Traffic Prediction- and Explainable Artificial Intelligence-Based Dynamic Routing in Software-Defined Elastic Optical Networks2024 IFIP Networking Conference (IFIP Networking)10.23919/IFIPNetworking62109.2024.10619798(750-756)Online publication date: 3-Jun-2024
https://doi.org/10.23919/IFIPNetworking62109.2024.10619798
Pérez PFiandrino CFiore MWidmer J(2024)An In-Depth Analysis of Advanced Time Series Forecasting Models for the Open RANIEEE INFOCOM 2024 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS)10.1109/INFOCOMWKSHPS61880.2024.10620742(1-6)Online publication date: 20-May-2024
https://doi.org/10.1109/INFOCOMWKSHPS61880.2024.10620742

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Table of Contents