A new weighted ensemble model for phishing detection based on feature selection

TL;DR

This paper introduces a weighted ensemble model for phishing website detection that leverages feature selection and standardization to improve identification accuracy, addressing the increasing cyber threat of phishing attacks.

Contribution

It proposes a novel weighted ensemble approach combined with feature selection and standardization, enhancing phishing detection performance over existing methods.

Findings

Improved detection accuracy after feature selection

Effective combination of multiple models with weighted voting

Enhanced model robustness through data standardization

Abstract

A phishing attack is a sort of cyber assault in which the attacker sends fake communications to entice a human victim to provide personal information or credentials. Phishing website identification can assist visitors in avoiding becoming victims of these assaults. The phishing problem is increasing day by day, and there is no single solution that can properly mitigate all vulnerabilities, thus many techniques are used. In this paper, We have proposed an ensemble model that combines multiple base models with a voting technique based on the weights. Moreover, we applied feature selection methods and standardization on the dataset effectively and compared the result before and after applying any feature selection.