The Application of Machine Learning Algorithms in Classification of Malicious Websites

Tabassom Sedighi; Reza Montasari; Amin Hosseinian Far

doi:10.1007/978-3-030-91218-5_6

The Application of Machine Learning Algorithms in Classification of Malicious Websites

Tabassom Sedighi, Reza Montasari, Amin Hosseinian Far^*

^*Corresponding author for this work

Research output: Contribution to Book/Report › Chapter › peer-review

Abstract

This chapter compares three different machine learning techniques, i.e. Gaussian process classification, decision tree classification and support vector classification, based on their ability to learn and detect the attributes of a malicious website. The data used have all been sourced from HTTP headers, WHOIS lookups and DNS records. As a result, this does not require parsing of the website content. The data are first subjected to multiple steps of pre-processing including data formatting, missing value replacement, scaling and principal component analysis.

Original language	English
Title of host publication	Privacy, Security And Forensics in The Internet of Things (IoT)
Editors	Reza Montasari, Fiona Carroll, Ian Mitchell, Sukhvinder Hara, Rachel Bolton-King
Place of Publication	Cham
Publisher	Springer
Chapter	6
Pages	131-147
Number of pages	17
ISBN (Electronic)	978-3-030-91218-5
ISBN (Print)	978-3-030-91217-8
DOIs	https://doi.org/10.1007/978-3-030-91218-5_6
Publication status	Published - 1 Jan 2022

Access to Document

10.1007/978-3-030-91218-5_6

Sedighi_etal_Springer_2022_The_Application_of_Machine_Learning_Algorithms_in_Classification_of_Malicious_WebsitesAccepted author manuscript, 710 KB

https://link.springer.com/chapter/10.1007/978-3-030-91218-5_6

Cite this

@inbook{5f9d0cd69f354ce5909e434f67b87eca,

title = "The Application of Machine Learning Algorithms in Classification of Malicious Websites",

abstract = "This chapter compares three different machine learning techniques, i.e. Gaussian process classification, decision tree classification and support vector classification, based on their ability to learn and detect the attributes of a malicious website. The data used have all been sourced from HTTP headers, WHOIS lookups and DNS records. As a result, this does not require parsing of the website content. The data are first subjected to multiple steps of pre-processing including data formatting, missing value replacement, scaling and principal component analysis.",

author = "Tabassom Sedighi and Reza Montasari and {Hosseinian Far}, Amin",

year = "2022",

month = jan,

day = "1",

doi = "10.1007/978-3-030-91218-5_6",

language = "English",

isbn = "978-3-030-91217-8",

pages = "131--147",

editor = "Reza Montasari and Fiona Carroll and Ian Mitchell and Sukhvinder Hara and Rachel Bolton-King",

booktitle = "Privacy, Security And Forensics in The Internet of Things (IoT)",

publisher = "Springer",

}

The Application of Machine Learning Algorithms in Classification of Malicious Websites. / Sedighi, Tabassom; Montasari, Reza; Hosseinian Far, Amin.
Privacy, Security And Forensics in The Internet of Things (IoT). ed. / Reza Montasari; Fiona Carroll; Ian Mitchell; Sukhvinder Hara; Rachel Bolton-King. Cham: Springer, 2022. p. 131-147.

Research output: Contribution to Book/Report › Chapter › peer-review

TY - CHAP

T1 - The Application of Machine Learning Algorithms in Classification of Malicious Websites

AU - Sedighi, Tabassom

AU - Montasari, Reza

AU - Hosseinian Far, Amin

PY - 2022/1/1

Y1 - 2022/1/1

N2 - This chapter compares three different machine learning techniques, i.e. Gaussian process classification, decision tree classification and support vector classification, based on their ability to learn and detect the attributes of a malicious website. The data used have all been sourced from HTTP headers, WHOIS lookups and DNS records. As a result, this does not require parsing of the website content. The data are first subjected to multiple steps of pre-processing including data formatting, missing value replacement, scaling and principal component analysis.

AB - This chapter compares three different machine learning techniques, i.e. Gaussian process classification, decision tree classification and support vector classification, based on their ability to learn and detect the attributes of a malicious website. The data used have all been sourced from HTTP headers, WHOIS lookups and DNS records. As a result, this does not require parsing of the website content. The data are first subjected to multiple steps of pre-processing including data formatting, missing value replacement, scaling and principal component analysis.

U2 - 10.1007/978-3-030-91218-5_6

DO - 10.1007/978-3-030-91218-5_6

M3 - Chapter

SN - 978-3-030-91217-8

SP - 131

EP - 147

BT - Privacy, Security And Forensics in The Internet of Things (IoT)

A2 - Montasari, Reza

A2 - Carroll, Fiona

A2 - Mitchell, Ian

A2 - Hara, Sukhvinder

A2 - Bolton-King, Rachel

PB - Springer

CY - Cham

ER -

The Application of Machine Learning Algorithms in Classification of Malicious Websites

Abstract

Access to Document

Fingerprint

Cite this