Benchmarking machine learning techniques for phishing detection and secure URL classification

Owa, K ORCID: https://orcid.org/0000-0002-1393-705X and Adewole, O, 2025. Benchmarking machine learning techniques for phishing detection and secure URL classification. International Journal of Computer Science and Mobile Computing, 14 (1), pp. 20-37. ISSN 2320-088X

Preview

Text 2345899_Owa.pdf - Post-print Download (958kB) | Preview

Abstract

Phishing is still one of the biggest threats in cybersecurity due to the exploitation of the users through the use of deceptive URLs. In this study, the outcomes of the Random Forest, Support Vector Machines, and Decision Trees models are analysed on databases containing more than 640,000 URLs. Comparing the results obtained from Random Forest using accuracy, precision, recall, and computational time, the results showed that it recorded the highest accuracy of 87.85\% on the Aalto dataset and 86.86\% on the Kaggle dataset. These perspectives provide a more fact-based approach towards developing more effective possession of enhanced practical anti-phishing systems.

Item Type:	Journal article
Publication Title:	International Journal of Computer Science and Mobile Computing
Creators:	Owa, K. and Adewole, O.
Publisher:	Zain Publications
Date:	January 2025
Volume:	14
Number:	1
ISSN:	2320-088X
Identifiers:	Number Type 10.47760/ijcsmc.2025.v14i01.003 DOI 2345899 Other
Divisions:	Schools > School of Science and Technology
Record created by:	Laura Borcherds
Date Added:	22 Jan 2025 13:58
Last Modified:	22 Jan 2025 13:58
URI:	https://irep.ntu.ac.uk/id/eprint/52910

Actions (login required)

Edit View

Statistics

Views

Downloads