Machine Learning Fingerprinting Methods in Cyber Security
Domain: Which one to Use?

D 2018

Machine Learning Fingerprinting Methods in Cyber Security Domain: Which one to Use?

LAŠTOVIČKA, Martin; Antonín DUFKA a Jana KOMÁRKOVÁ

Základní údaje

Originální název

Machine Learning Fingerprinting Methods in Cyber Security Domain: Which one to Use?

Autoři

LAŠTOVIČKA, Martin ; Antonín DUFKA a Jana KOMÁRKOVÁ

Vydání

Limassol, Cyprus, Proceedings of the 14th International Wireless Communications and Mobile Computing Conference, od s. 542-547, 6 s. 2018

Nakladatel

IEEE Xplore Digital Library

Další údaje

Jazyk

angličtina

Typ výsledku

Stať ve sborníku

Obor

10201 Computer sciences, information science, bioinformatics

Stát vydavatele

Spojené státy

Utajení

není předmětem státního či obchodního tajemství

Forma vydání

elektronická verze "online"

Odkazy

URL

Označené pro přenos do RIV

Ano

Kód RIV

RIV/00216224:14610/18:00106888

Organizační jednotka

Ústav výpočetní techniky

ISBN

978-1-5386-2070-0

ISSN

Klíčová slova anglicky

Machine Learning; OS Fingerprinting; IPFIX; Cybersecurity

Štítky

core_B, firank_B, rivok

Příznaky

Mezinárodní význam, Recenzováno

Změněno: 26. 4. 2019 08:47, RNDr. Martin Laštovička, Ph.D.

Anotace

V originále

Identification of a communicating device operating system is a fundamental part of network situational awareness. However, current networks are large and change often which implies the need for a system that will be able to continuously monitor the network and handle changes in identified operating systems. The aim of this paper is to compare machine learning methods performance for OS fingerprinting on real-world data in the terms of processing time, memory requirements, and performance measures of accuracy, precision, and recall.

Návaznosti

VI20172020070, projekt VaV

Název: Výzkum nástrojů pro hodnocení kybernetické situace a podporu rozhodování CSIRT týmů při ochraně kritické infrastruktury (Akronym: CRUSOE)

Investor: Ministerstvo vnitra ČR, Výzkum nástrojů pro hodnocení kybernetické situace a podporu rozhodování CSIRT týmů při ochraně kritické infrastruktury

Přiložené soubory

2018-DACS-machine-learning-fingerprinting-methods-in-cyber-security-domain-which-one-to-use-paper.pdf Verze souboru

2018-DACS-machine-learning-fingerprinting-methods-in-cyber-security-domain-which-one-to-use-presentation.pdf

Citovat

LAŠTOVIČKA, Martin; Antonín DUFKA a Jana KOMÁRKOVÁ. Machine Learning Fingerprinting Methods in Cyber Security Domain: Which one to Use?. Online. In IEEE. Proceedings of the 14th International Wireless Communications and Mobile Computing Conference. Limassol, Cyprus: IEEE Xplore Digital Library, 2018, s. 542-547. ISBN 978-1-5386-2070-0. Dostupné z: https://doi.org/10.1109/IWCMC.2018.8450406.

@inproceedings{1420614,
   author = {Laštovička, Martin and Dufka, Antonín and Komárková, Jana},
   address = {Limassol, Cyprus},
   booktitle = {Proceedings of the 14th International Wireless Communications and Mobile Computing Conference},
   doi = {https://doi.org/10.1109/IWCMC.2018.8450406},
   editor = {IEEE},
   keywords = {Machine Learning; OS Fingerprinting; IPFIX; Cybersecurity},
   howpublished = {elektronická verze "online"},
   language = {eng},
   location = {Limassol, Cyprus},
   isbn = {978-1-5386-2070-0},
   pages = {542-547},
   publisher = {IEEE Xplore Digital Library},
   title = {Machine Learning Fingerprinting Methods in Cyber Security Domain: Which one to Use?},
   url = {https://ieeexplore.ieee.org/abstract/document/8450406},
   year = {2018}
}

TY  - CONF
ID  - 1420614
AU  - Laštovička, Martin - Dufka, Antonín - Komárková, Jana
PY  - 2018
TI  - Machine Learning Fingerprinting Methods in Cyber Security Domain: Which one to Use?
PB  - IEEE Xplore Digital Library
CY  - Limassol, Cyprus
SN  - 9781538620700
KW  - Machine Learning
KW  - OS Fingerprinting
KW  - IPFIX
KW  - Cybersecurity
UR  - https://ieeexplore.ieee.org/abstract/document/8450406
L2  - https://ieeexplore.ieee.org/abstract/document/8450406
N2  - Identification of a communicating device operating system is a fundamental part of network situational awareness. However, current networks are large and change often which implies the need for a system that will be able to continuously monitor the network and handle changes in identified operating systems. The aim of this paper is to compare machine learning methods performance for OS fingerprinting on real-world data in the terms of processing time, memory requirements, and performance measures of accuracy, precision, and recall.
ER  -

LAŠTOVIČKA, Martin; Antonín DUFKA a Jana KOMÁRKOVÁ. Machine Learning Fingerprinting Methods in Cyber Security Domain: Which one to Use?. Online. In IEEE. \textit{Proceedings of the 14th International Wireless Communications and Mobile Computing Conference}. Limassol, Cyprus: IEEE Xplore Digital Library, 2018, s.~542-547. ISBN~978-1-5386-2070-0. Dostupné z: https://doi.org/10.1109/IWCMC.2018.8450406.

Přehled o publikaci