A First Look at Class Incremental Learning in Deep Learning Mobile Traffic Classification

The recent popularity growth of Deep Learning (DL) re-ignited the interest towards traffic classification, with several studies demonstrating the accuracy of DL-based classifiers to identify Internet applications’ traffic. Even with the aid of hardware accelerators (GPUs, TPUs), DL model training remains expensive, and limits the ability to operate frequent model updates necessary to fit to the ever evolving nature of Internet traffic, and mobile traffic in particular. To address this pain point, in this work we explore Incremental Learning (IL) techniques to add new classes to models without a full retraining, hence speeding up model’s updates cycle. We consider iCarl, a state of the art IL method, and MIRAGE-2019, a public dataset with traffic from 40 Android apps, aiming to understand if there is a case for incremental learning in traffic classification. By dissecting iCarl internals, we discuss ways to improve its design, contributing a revised version, namely iCarl+. Despite our analysis reveals their infancy, IL techniques are a promising research area on the roadmap towards automated DL-based traffic analysis systems.

[1]  Guanglu Sun,et al.  Internet Traffic Classification Based on Incremental Support Vector Machines , 2018, Mob. Networks Appl..

[2]  Giuseppe Aceto,et al.  MIRAGE: Mobile-app Traffic Capture and Ground-truth Creation , 2019, 2019 4th International Conference on Computing, Communications and Security (ICCCS).

[3]  Ricard Gavaldà,et al.  Adaptive Learning from Evolving Data Streams , 2009, IDA.

[4]  Max Welling,et al.  Herding dynamical weights to learn , 2009, ICML '09.

[5]  Antonio Pescapè,et al.  Mobile Encrypted Traffic Classification Using Deep Learning , 2018, 2018 Network Traffic Measurement and Analysis Conference (TMA).

[6]  Tinne Tuytelaars,et al.  Expert Gate: Lifelong Learning with a Network of Experts , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Dario Rossi,et al.  Wire-speed statistical classification of network traffic on commodity hardware , 2012, Internet Measurement Conference.

[8]  Maurizio Dusi,et al.  Traffic classification through simple statistical fingerprinting , 2007, CCRV.

[9]  Renata Teixeira,et al.  Traffic classification on the fly , 2006, CCRV.

[10]  Pavel Celeda,et al.  A survey of methods for encrypted traffic classification and analysis , 2015, Int. J. Netw. Manag..

[11]  Jaime Lloret,et al.  Network Traffic Classifier With Convolutional and Recurrent Neural Networks for Internet of Things , 2017, IEEE Access.

[12]  Svetlana Lazebnik,et al.  PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruning , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[13]  Ming Zhu,et al.  End-to-end encrypted traffic classification with one-dimensional convolution neural networks , 2017, 2017 IEEE International Conference on Intelligence and Security Informatics (ISI).

[14]  Matthieu Guillaumin,et al.  Incremental Learning of NCM Forests for Large-Scale Image Classification , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[15]  Muhammad N. Marsono,et al.  Online Incremental Learning for High Bandwidth Network Traffic Classification , 2016, Appl. Comput. Intell. Soft Comput..

[16]  Christoph H. Lampert,et al.  iCaRL: Incremental Classifier and Representation Learning , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Geoff Holmes,et al.  Batch-Incremental versus Instance-Incremental Learning in Dynamic and Evolving Data , 2012, IDA.

[18]  Latifur Khan,et al.  Incremental Ensemble Classifier Addressing Non-stationary Fast Data Streams , 2014, 2014 IEEE International Conference on Data Mining Workshop.

[19]  Andreas Krause,et al.  Coresets via Bilevel Optimization for Continual Learning and Streaming , 2020, NeurIPS.

[20]  Kensuke Fukuda,et al.  A streaming flow-based technique for traffic classification applied to 12 + 1 years of Internet traffic , 2016, Telecommun. Syst..

[21]  Grenville J. Armitage,et al.  A survey of techniques for internet traffic classification using machine learning , 2008, IEEE Communications Surveys & Tutorials.

[22]  Derek Hoiem,et al.  Learning without Forgetting , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[23]  Fuhao Li,et al.  Autonomous Unknown-Application Filtering and Labeling for DL-based Traffic Classifier Update , 2020, IEEE INFOCOM 2020 - IEEE Conference on Computer Communications.

[24]  Andreas S. Tolias,et al.  Three scenarios for continual learning , 2019, ArXiv.

[25]  Mahdi Jafari Siavoshani,et al.  Deep packet: a novel approach for encrypted traffic classification using deep learning , 2017, Soft Computing.

[26]  Adrian Popescu,et al.  ScaIL: Classifier Weights Scaling for Class Incremental Learning , 2020, 2020 IEEE Winter Conference on Applications of Computer Vision (WACV).

[27]  Michael McCloskey,et al.  Catastrophic Interference in Connectionist Networks: The Sequential Learning Problem , 1989 .

[28]  Cedric Baudoin,et al.  Towards the Deployment of Machine Learning Solutions in Network Traffic Classification: A Systematic Survey , 2019, IEEE Communications Surveys & Tutorials.

[29]  Jingyu Wang,et al.  Common Knowledge Based and One-Shot Learning Enabled Multi-Task Traffic Classification , 2019, IEEE Access.

[30]  Ronald Kemker,et al.  FearNet: Brain-Inspired Model for Incremental Learning , 2017, ICLR.

[31]  Christopher Kanan,et al.  REMIND Your Neural Network to Prevent Catastrophic Forgetting , 2020, ECCV.

[32]  Kibok Lee,et al.  A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks , 2018, NeurIPS.

[33]  Yoshua Bengio,et al.  An Empirical Investigation of Catastrophic Forgeting in Gradient-Based Neural Networks , 2013, ICLR.

[34]  Cordelia Schmid,et al.  End-to-End Incremental Learning , 2018, ECCV.

[35]  Jiwon Kim,et al.  Continual Learning with Deep Generative Replay , 2017, NIPS.

[36]  Geoffrey E. Hinton,et al.  Distilling the Knowledge in a Neural Network , 2015, ArXiv.

[37]  Xin Liu,et al.  Multitask Learning for Network Traffic Classification , 2019, 2020 29th International Conference on Computer Communications and Networks (ICCCN).

[38]  Xinlei Chen,et al.  Never-Ending Learning , 2012, ECAI.

[39]  Ricard Gavaldà,et al.  Learning from Time-Changing Data with Adaptive Windowing , 2007, SDM.

[40]  Diego Perino,et al.  Tackling Mobile Traffic Critical Path Analysis With Passive and Active Measurements , 2019, 2019 Network Traffic Measurement and Analysis Conference (TMA).

[41]  Adrian Popescu,et al.  A Comprehensive Study of Class Incremental Learning Algorithms for Visual Tasks , 2020, Neural Networks.

[42]  Philip S. Yu,et al.  Mining concept-drifting data streams using ensemble classifiers , 2003, KDD '03.

[43]  Gabriela Csurka,et al.  Distance-Based Image Classification: Generalizing to New Classes at Near-Zero Cost , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[44]  Yandong Guo,et al.  Large Scale Incremental Learning , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).