Deep Learning For Cyber Security in the Internet of Things (IoT) Network

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216275%3A25410%2F23%3A39920282" target="_blank" >RIV/00216275:25410/23:39920282 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.35011/IDIMT-2023-391" target="_blank" >http://dx.doi.org/10.35011/IDIMT-2023-391</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.35011/IDIMT-2023-391" target="_blank" >10.35011/IDIMT-2023-391</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Deep Learning For Cyber Security in the Internet of Things (IoT) Network

Popis výsledku v původním jazyce

The Internet of Things (IoT) is a swiftly evolving paradigm having the potential to transform thephysical interaction between individuals and organizations. IoT has applications in multiple fieldssuch as healthcare, education, resource management, and information processing to name a few.Many organizations rely greatly on technology, and most are changing their process into intelligentor smart solutions. Moreover, these networks are wireless, self-configuring, do not need preexisting infrastructure, and have a large unpredictable node movement; security becomes one of themost crucial concerns that need to be addressed. In this paper, we proposed an intrusion preventionmethod that uses a federated deep learning-based framework. A real IoT traffic dataset will be usedto train the state-of-the-art graph neural network algorithm. A comparison will be carried outbased on different experimental results. Finally, this work contributes to the security of IoTnetworks through the implementation of effective tools/techniques for timely IoT attackclassification and mitigation.

Název v anglickém jazyce

Deep Learning For Cyber Security in the Internet of Things (IoT) Network

Popis výsledku anglicky

The Internet of Things (IoT) is a swiftly evolving paradigm having the potential to transform thephysical interaction between individuals and organizations. IoT has applications in multiple fieldssuch as healthcare, education, resource management, and information processing to name a few.Many organizations rely greatly on technology, and most are changing their process into intelligentor smart solutions. Moreover, these networks are wireless, self-configuring, do not need preexisting infrastructure, and have a large unpredictable node movement; security becomes one of themost crucial concerns that need to be addressed. In this paper, we proposed an intrusion preventionmethod that uses a federated deep learning-based framework. A real IoT traffic dataset will be usedto train the state-of-the-art graph neural network algorithm. A comparison will be carried outbased on different experimental results. Finally, this work contributes to the security of IoTnetworks through the implementation of effective tools/techniques for timely IoT attackclassification and mitigation.

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

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2023

Kód důvěrnosti údajů

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

Název statě ve sborníku

IDIMT-2023 : New Challenges for ICT and Management : 31st Interdisciplinary Information Management

ISBN

978-3-99151-176-2

ISSN

—

e-ISSN

—

Počet stran výsledku

8

Strana od-do

391-398

Název nakladatele

Trauner Verlag

Místo vydání

Linz

Místo konání akce

Hradec Králové

Datum konání akce

6. 9. 2023

Typ akce podle státní příslušnosti

EUR - Evropská akce

Kód UT WoS článku

—