Using a Machine Learning Model for Malicious URL Type Detection

Suet Ping Tung; Ka Yan Wong; Ievgeniia Kuzminykh; Taimur Bakhshi; Bogdan Ghita

doi:10.1007/978-3-030-97777-1_41

Using a Machine Learning Model for Malicious URL Type Detection

Suet Ping Tung, Ka Yan Wong, Ievgeniia Kuzminykh, Taimur Bakhshi, Bogdan Ghita

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

The world wide web, beyond its benefits, has also become a major platform for online criminal activities. Traditional protection methods against malicious URLs, such as blacklisting, remain a valid alternative, but cannot detect unknown sites, hence new methods are being developed for automatic detection, using machine learning approaches. This paper strengthens the existing state of the art by proposing an alternative machine learning approach, that uses a set of 14 lexical and host-based features but focuses on the typical mechanisms employed by malicious URLs. The proposed method employs random forest and decision tree as core mechanisms and is evaluated on a combined benign and malicious URL dataset, which indicates an accuracy of over 97%.

Original language	English
Title of host publication	Internet of Things, Smart Spaces, and Next Generation Networks and Systems
Subtitle of host publication	21st International Conference, NEW2AN 2021, and 14th Conference, ruSMART 2021, St. Petersburg, Russia, August 26–27, 2021, Proceedings
Editors	Yevgeni Koucheryavy, Sergey Balandin, Sergey Andreev
Publisher	Springer
Pages	493-505
Number of pages	13
ISBN (Electronic)	978-3-030-97777-1
ISBN (Print)	978-3-030-97776-4
DOIs	https://doi.org/10.1007/978-3-030-97777-1_41
Publication status	Published - 16 Mar 2022
Externally published	Yes
Event	21st International Conference on Next Generation Wired/Wireless Networks and Systems - Online, St, Petersburg, Russian Federation Duration: 30 Aug 2021 → 31 Aug 2021

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer
Volume	13158
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	21st International Conference on Next Generation Wired/Wireless Networks and Systems
Abbreviated title	NEW2AN 2021
Country/Territory	Russian Federation
City	St, Petersburg
Period	30/08/21 → 31/08/21

Keywords

Malicious URL
Web security
Machine Learning
Phishing
Spamming
Malware
Lexical Feature
Traffic

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-3-030-97777-1_41

Cite this

Tung, S. P., Wong, K. Y., Kuzminykh, I., Bakhshi, T., & Ghita, B. (2022). Using a Machine Learning Model for Malicious URL Type Detection. In Y. Koucheryavy, S. Balandin, & S. Andreev (Eds.), Internet of Things, Smart Spaces, and Next Generation Networks and Systems: 21st International Conference, NEW2AN 2021, and 14th Conference, ruSMART 2021, St. Petersburg, Russia, August 26–27, 2021, Proceedings (pp. 493-505). (Lecture Notes in Computer Science; Vol. 13158). Springer. https://doi.org/10.1007/978-3-030-97777-1_41

Tung, Suet Ping ; Wong, Ka Yan ; Kuzminykh, Ievgeniia et al. / Using a Machine Learning Model for Malicious URL Type Detection. Internet of Things, Smart Spaces, and Next Generation Networks and Systems: 21st International Conference, NEW2AN 2021, and 14th Conference, ruSMART 2021, St. Petersburg, Russia, August 26–27, 2021, Proceedings. editor / Yevgeni Koucheryavy ; Sergey Balandin ; Sergey Andreev. Springer, 2022. pp. 493-505 (Lecture Notes in Computer Science).

@inproceedings{db8d98ee495248b6839f7abbf264c84f,

title = "Using a Machine Learning Model for Malicious URL Type Detection",

abstract = "The world wide web, beyond its benefits, has also become a major platform for online criminal activities. Traditional protection methods against malicious URLs, such as blacklisting, remain a valid alternative, but cannot detect unknown sites, hence new methods are being developed for automatic detection, using machine learning approaches. This paper strengthens the existing state of the art by proposing an alternative machine learning approach, that uses a set of 14 lexical and host-based features but focuses on the typical mechanisms employed by malicious URLs. The proposed method employs random forest and decision tree as core mechanisms and is evaluated on a combined benign and malicious URL dataset, which indicates an accuracy of over 97%.",

keywords = "Malicious URL, Web security, Machine Learning, Phishing, Spamming, Malware, Lexical Feature, Traffic",

author = "Tung, {Suet Ping} and Wong, {Ka Yan} and Ievgeniia Kuzminykh and Taimur Bakhshi and Bogdan Ghita",

note = "Publisher Copyright: {\textcopyright} 2022, Springer Nature Switzerland AG.; 21st International Conference on Next Generation Wired/Wireless Networks and Systems, NEW2AN 2021 ; Conference date: 30-08-2021 Through 31-08-2021",

year = "2022",

month = mar,

day = "16",

doi = "10.1007/978-3-030-97777-1_41",

language = "English",

isbn = "978-3-030-97776-4",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "493--505",

editor = "Yevgeni Koucheryavy and Sergey Balandin and Sergey Andreev",

booktitle = "Internet of Things, Smart Spaces, and Next Generation Networks and Systems",

address = "Germany",

}

Tung, SP, Wong, KY, Kuzminykh, I, Bakhshi, T & Ghita, B 2022, Using a Machine Learning Model for Malicious URL Type Detection. in Y Koucheryavy, S Balandin & S Andreev (eds), Internet of Things, Smart Spaces, and Next Generation Networks and Systems: 21st International Conference, NEW2AN 2021, and 14th Conference, ruSMART 2021, St. Petersburg, Russia, August 26–27, 2021, Proceedings. Lecture Notes in Computer Science, vol. 13158, Springer, pp. 493-505, 21st International Conference on Next Generation Wired/Wireless Networks and Systems, St, Petersburg, Russian Federation, 30/08/21. https://doi.org/10.1007/978-3-030-97777-1_41

Using a Machine Learning Model for Malicious URL Type Detection. / Tung, Suet Ping; Wong, Ka Yan; Kuzminykh, Ievgeniia et al.
Internet of Things, Smart Spaces, and Next Generation Networks and Systems: 21st International Conference, NEW2AN 2021, and 14th Conference, ruSMART 2021, St. Petersburg, Russia, August 26–27, 2021, Proceedings. ed. / Yevgeni Koucheryavy; Sergey Balandin; Sergey Andreev. Springer, 2022. p. 493-505 (Lecture Notes in Computer Science; Vol. 13158).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Using a Machine Learning Model for Malicious URL Type Detection

AU - Tung, Suet Ping

AU - Wong, Ka Yan

AU - Kuzminykh, Ievgeniia

AU - Bakhshi, Taimur

AU - Ghita, Bogdan

PY - 2022/3/16

Y1 - 2022/3/16

N2 - The world wide web, beyond its benefits, has also become a major platform for online criminal activities. Traditional protection methods against malicious URLs, such as blacklisting, remain a valid alternative, but cannot detect unknown sites, hence new methods are being developed for automatic detection, using machine learning approaches. This paper strengthens the existing state of the art by proposing an alternative machine learning approach, that uses a set of 14 lexical and host-based features but focuses on the typical mechanisms employed by malicious URLs. The proposed method employs random forest and decision tree as core mechanisms and is evaluated on a combined benign and malicious URL dataset, which indicates an accuracy of over 97%.

AB - The world wide web, beyond its benefits, has also become a major platform for online criminal activities. Traditional protection methods against malicious URLs, such as blacklisting, remain a valid alternative, but cannot detect unknown sites, hence new methods are being developed for automatic detection, using machine learning approaches. This paper strengthens the existing state of the art by proposing an alternative machine learning approach, that uses a set of 14 lexical and host-based features but focuses on the typical mechanisms employed by malicious URLs. The proposed method employs random forest and decision tree as core mechanisms and is evaluated on a combined benign and malicious URL dataset, which indicates an accuracy of over 97%.

KW - Malicious URL

KW - Web security

KW - Machine Learning

KW - Phishing

KW - Spamming

KW - Malware

KW - Lexical Feature

KW - Traffic

U2 - 10.1007/978-3-030-97777-1_41

DO - 10.1007/978-3-030-97777-1_41

M3 - Conference contribution

SN - 978-3-030-97776-4

T3 - Lecture Notes in Computer Science

SP - 493

EP - 505

BT - Internet of Things, Smart Spaces, and Next Generation Networks and Systems

A2 - Koucheryavy, Yevgeni

A2 - Balandin, Sergey

A2 - Andreev, Sergey

PB - Springer

T2 - 21st International Conference on Next Generation Wired/Wireless Networks and Systems

Y2 - 30 August 2021 through 31 August 2021

ER -

Tung SP, Wong KY, Kuzminykh I, Bakhshi T, Ghita B. Using a Machine Learning Model for Malicious URL Type Detection. In Koucheryavy Y, Balandin S, Andreev S, editors, Internet of Things, Smart Spaces, and Next Generation Networks and Systems: 21st International Conference, NEW2AN 2021, and 14th Conference, ruSMART 2021, St. Petersburg, Russia, August 26–27, 2021, Proceedings. Springer. 2022. p. 493-505. (Lecture Notes in Computer Science). doi: 10.1007/978-3-030-97777-1_41

Using a Machine Learning Model for Malicious URL Type Detection

Abstract

Publication series

Conference

Keywords

UN SDGs

Access to Document

Fingerprint

Cite this