University of Leicester
Browse
1610.06089v1.pdf (438.4 kB)

Finding Clustering Configurations to Accurately Infer Packet Structures from Network Data

Download (438.4 kB)
preprint
posted on 2017-08-30, 08:10 authored by Othman Esoul, Neil Walkinshaw
Clustering is often used for reverse engineering network protocols from captured network traces. The performance of clustering techniques is often contingent upon the selection of various parameters, which can have a severe impact on clustering quality. In this paper we experimentally investigate the effect of four different parameters with respect to network traces. We also determining the optimal parameter configuration with respect to traces from four different network protocols. Our results indicate that the choice of distance measure and the length of the message has the most substantial impact on cluster accuracy. Depending on the type of protocol, the $n$-gram length can also have a substantial impact.

History

Citation

arXiv:1610.06089 [cs.NI], 2016

Author affiliation

/Organisation/COLLEGE OF SCIENCE AND ENGINEERING/Department of Computer Science

Version

  • AO (Author's Original)

Published in

arXiv:1610.06089 [cs.NI]

Acceptance date

2016-10-19

Copyright date

2016

Available date

2017-08-30

Publisher version

https://arxiv.org/abs/1610.06089

Language

en

Usage metrics

    University of Leicester Publications

    Categories

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC