A Few Shots Traffic Classification with mini-FlowPic Augmentations

Eyal Horowicz, Tal Shapira, Yuval Shavitt

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Scopus citations


Internet traffic classification has been intensively studied over the past decade due to its importance for traffic engineering and cyber security. One of the best solutions to several traffic classification problems is the FlowPic approach, where histograms of packet sizes in consecutive time slices are transformed into a picture that is fed into a Convolution Neural Network (CNN) model for classification. However, CNNs (and the FlowPic approach included) require a relatively large labeled flow dataset, which is not always easy to obtain. In this paper, we show that we can overcome this obstacle by replacing the large labeled dataset with a few samples of each class and by using augmentations in order to inflate the number of training samples. We show that common picture augmentation techniques can help, but accuracy improves further when introducing augmentation techniques that mimic network behavior such as changes in the RTT. Finally, we show that we can replace the large FlowPics suggested in the past with much smaller mini-FlowPics and achieve two advantages: improved model performance and easier engineering. Interestingly, this even improves accuracy in some cases.

Original languageEnglish
Title of host publicationIMC 2022 - Proceedings of the 2022 ACM Internet Measurement Conference
PublisherAssociation for Computing Machinery
Number of pages8
ISBN (Electronic)9781450392594
StatePublished - 25 Oct 2022
Event22nd ACM Internet Measurement Conference, IMC 2022 - Nice, France
Duration: 25 Oct 202227 Oct 2022

Publication series

NameProceedings of the ACM SIGCOMM Internet Measurement Conference, IMC


Conference22nd ACM Internet Measurement Conference, IMC 2022


FundersFunder number
Israeli PMO
Tel Aviv University


    Dive into the research topics of 'A Few Shots Traffic Classification with mini-FlowPic Augmentations'. Together they form a unique fingerprint.

    Cite this