URL-BASED PHISHING DETECTION USING HYBRID ENSEMBLE TECHNIQUE

Nurhashikin Mohd Salleh; Siti Rahayu Selamat

doi:10.54554/jacta.2025.07.02.003

Authors

Nurhashikin Mohd Salleh
Siti Rahayu Selamat

DOI:

https://doi.org/10.54554/jacta.2025.07.02.003

Keywords:

Phishing Attacks, ; Hybrid Ensemble Technique, Uniform Resource Locator (URL), WEKA (Waikato Environment for Knowledge Analysis)

Abstract

Phishing attacks produces a huge and developing menace or threat. These sneaky approaches are intended to gain important data by acting as authentic characters which leads to huge monetary and perception destruction for individuals and institutions alike. Over the years, phishing methods have become more and more refined, making it essential to develop strong detection systems. There is a serious urgency to study and analyze the efficiency of hybrid ensemble method against the traditional and ensemble method in detecting phishing websites. Based on this reason, this paper proposes the hybrid ensemble classification methods in detection phishing attacks from Uniform Resource Locator (URL). The dataset has been downloaded from the UCI Machine Learning Repository. The project is made up of three major steps, which are Data Collection, Pre-Processing, and Hybrid Ensemble Model. Three types of hybrid ensemble techniques were tested, and the hybrid version of the Random Forest Classifier with stacking proved to be the most effective, achieving an accuracy of 97.21%. The result indicates that this technique significantly improves classification performance compared to the other ensemble methods.

Downloads

Download data is not yet available.

References

G.Buket, K. Erensoy and E. Kocyigit, "Detection of phishing websites from URLs by using classification techniques on WEKA." 2021 6th International Conference on Inventive Computation Technologies (ICICT). IEEE, 2021.

G. Sonowal, “Introduction to phishing” In Phishing and Communication Channels: A Guide to Identifying and Mitigating Phishing Attacks, pp. 1-24. Berkeley, CA: Apress, 2021.

Z.Alkhalil, C.Hewage, L.Nawaf and I. Khan, “Phishing attacks: A recent comprehensive study and a new anatomy. Frontiers in Computer Science, 3, 563060, 2021.

M. S. Kheruddin, M. A. E. M. Zuber and M. M. M. Radzai, “Phishing attacks: Unraveling tactics, threats, and defenses in the cybersecurity landscape” Authorea Preprints, 2024.

M.Madleňák and K.Kampová, “Phishing as a cyber security threat”, In 2022 20th international conference on emerging elearning technologies and applications (ICETA), IEEE, pp. 392-396, 2022.

A.Karim, M.Shahroz, K. Mustofa, , S. B. Belhaouari and S. R. K. Joga, “Phishing detection system through hybrid machine learning based on URL”, IEEE Access, 11, 36805-36822, 2023.

K.Omari, “Comparative study of machine learning algorithms for phishing website detection”, International Journal of Advanced Computer Science and Applications, vol.14, no.9, 2023.

A.Kulkarni and L. L. Brown, “Phishing Websites Detection using Machine Learning”, International Journal of Advanced Computer Science and Applications, vol. 10, 2019.

A. Soni and J. Tiwari, “Phishing Website Detection Using Ensemble Learning”, vol. 11, 2023.

Y. S.Tambe, S. S.Mhangore and K. S. Desai, “Phishing URL Detection Using Machine Learning”, Journal of Advanced Research in Production and Industrial Engineering, vol.10, no.1, pp. 1-5, 2023.

A.Basit, M.Zafar, , A. R.Javed, and Z.Jalil, “A novel ensemble machine learning method to detect phishing attack”, In 2020 IEEE 23rd International Multitopic Conference (INMIC), pp. 1-5, 2020.

M. H. Mumu, and T.Aishy, “Malicious URL detection using machine learning and deep learning algorithms”, Ph.D. dissertation, East West University, Bangladesh, 2023.