Behavior of the DenStream Clustering Algorithm for Attack Detection in the Internet of Things

Multiple attack detection schemes based on supervised batch learning are presented in the literature as an alternative to improve Internet of Things (IoT) security. These schemes require benign and malicious traffic samples for training and are unable to easily adapt to changes in the analyzed data...

Full description

Bibliographic Details
Main Authors: Gabriel Keith Tazima, Bruno Bogaz Zarpelao (COMP/UEL)
Format: Article
Language:English
Published: Universidade Estadual de Londrina 2023-12-01
Series:Semina: Ciências Exatas e Tecnológicas
Subjects:
Online Access:https://ojs.uel.br/revistas/uel/index.php/semexatas/article/view/48956
_version_ 1797226149895471104
author Gabriel Keith Tazima
Bruno Bogaz Zarpelao (COMP/UEL)
author_facet Gabriel Keith Tazima
Bruno Bogaz Zarpelao (COMP/UEL)
author_sort Gabriel Keith Tazima
collection DOAJ
description Multiple attack detection schemes based on supervised batch learning are presented in the literature as an alternative to improve Internet of Things (IoT) security. These schemes require benign and malicious traffic samples for training and are unable to easily adapt to changes in the analyzed data. In this work, we study how we can use DenStream, an unsupervised stream mining algorithm, to detect attacks in IoT networks. This type of algorithm does not require labeled examples and can learn incrementally, adapting to changes. We aim to investigate whether attacks can be detected by monitoring the behavior of DenStream's clusters. The results showed that DenStream could provide indicators of attack occurrence in TCP, UDP, and ICMP traffic.
first_indexed 2024-04-24T14:20:19Z
format Article
id doaj.art-4cc295fcc76d43c1baaaa0d29312d2cf
institution Directory Open Access Journal
issn 1676-5451
1679-0375
language English
last_indexed 2024-04-24T14:20:19Z
publishDate 2023-12-01
publisher Universidade Estadual de Londrina
record_format Article
series Semina: Ciências Exatas e Tecnológicas
spelling doaj.art-4cc295fcc76d43c1baaaa0d29312d2cf2024-04-03T06:53:36ZengUniversidade Estadual de LondrinaSemina: Ciências Exatas e Tecnológicas1676-54511679-03752023-12-014410.5433/1679-0375.2023.v44.48956Behavior of the DenStream Clustering Algorithm for Attack Detection in the Internet of ThingsGabriel Keith Tazima0Bruno Bogaz Zarpelao (COMP/UEL)1State University of Londrina - DC/UELState University of Londrina - DC\UEL Multiple attack detection schemes based on supervised batch learning are presented in the literature as an alternative to improve Internet of Things (IoT) security. These schemes require benign and malicious traffic samples for training and are unable to easily adapt to changes in the analyzed data. In this work, we study how we can use DenStream, an unsupervised stream mining algorithm, to detect attacks in IoT networks. This type of algorithm does not require labeled examples and can learn incrementally, adapting to changes. We aim to investigate whether attacks can be detected by monitoring the behavior of DenStream's clusters. The results showed that DenStream could provide indicators of attack occurrence in TCP, UDP, and ICMP traffic. https://ojs.uel.br/revistas/uel/index.php/semexatas/article/view/48956stream miningcyberattack detectioninternet of thingscybersecurity
spellingShingle Gabriel Keith Tazima
Bruno Bogaz Zarpelao (COMP/UEL)
Behavior of the DenStream Clustering Algorithm for Attack Detection in the Internet of Things
Semina: Ciências Exatas e Tecnológicas
stream mining
cyberattack detection
internet of things
cybersecurity
title Behavior of the DenStream Clustering Algorithm for Attack Detection in the Internet of Things
title_full Behavior of the DenStream Clustering Algorithm for Attack Detection in the Internet of Things
title_fullStr Behavior of the DenStream Clustering Algorithm for Attack Detection in the Internet of Things
title_full_unstemmed Behavior of the DenStream Clustering Algorithm for Attack Detection in the Internet of Things
title_short Behavior of the DenStream Clustering Algorithm for Attack Detection in the Internet of Things
title_sort behavior of the denstream clustering algorithm for attack detection in the internet of things
topic stream mining
cyberattack detection
internet of things
cybersecurity
url https://ojs.uel.br/revistas/uel/index.php/semexatas/article/view/48956
work_keys_str_mv AT gabrielkeithtazima behaviorofthedenstreamclusteringalgorithmforattackdetectionintheinternetofthings
AT brunobogazzarpelaocompuel behaviorofthedenstreamclusteringalgorithmforattackdetectionintheinternetofthings