Mobile Botnet Detection via Artificial Neural Networks

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F70883521%3A28140%2F17%3A63517333" target="_blank" >RIV/70883521:28140/17:63517333 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Mobile Botnet Detection via Artificial Neural Networks

Popis výsledku v původním jazyce

This paper deals with an area of cyber security and detection of the most dangerous category of mobile malware - botnets - via artificial neural networks. These specific pieces of mobile malware have a strange kind of behaviour. According to this pattern, botnets are not controlled by any expectable algorithm. On the contrary, humans managed their functioning via command and control servers (C&amp;C servers) or via peer-to-peer networks. Authors and their co-workers made an analysis of available current mobile botnets and they reveal some of their common features which were used later during training via artificial neural networks. The simulations were carried out with Levenberg-Marquardt training algorithm in the classical feed forward network. The results showed 100% successful training and almost 100% testing accuracy.

Název v anglickém jazyce

Mobile Botnet Detection via Artificial Neural Networks

Popis výsledku anglicky

This paper deals with an area of cyber security and detection of the most dangerous category of mobile malware - botnets - via artificial neural networks. These specific pieces of mobile malware have a strange kind of behaviour. According to this pattern, botnets are not controlled by any expectable algorithm. On the contrary, humans managed their functioning via command and control servers (C&amp;C servers) or via peer-to-peer networks. Authors and their co-workers made an analysis of available current mobile botnets and they reveal some of their common features which were used later during training via artificial neural networks. The simulations were carried out with Levenberg-Marquardt training algorithm in the classical feed forward network. The results showed 100% successful training and almost 100% testing accuracy.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2017

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

2017 International Conference on Logistics, Informatics and Service Sciences (LISS)

ISBN

978-1-5386-1047-3

ISSN

—

e-ISSN

neuvedeno

Počet stran výsledku

5

Strana od-do

157-161

Název nakladatele

IEEE

Místo vydání

New Jersey, Piscataway

Místo konání akce

Kyoto

Datum konání akce

24. 7. 2017

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—