# Fuzzy Rough Set Feature Selection to Enhance Phishing Attack Detection

## TL;DR

This paper introduces a fuzzy rough set-based feature selection method to improve phishing website detection, achieving high accuracy with a universal feature set that is fast and robust against zero-day attacks.

## Contribution

It applies Fuzzy Rough Set theory for effective feature selection in phishing detection, identifying a universal feature set that enhances speed and robustness without external data.

## Key findings

- Maximum F-measure of 95% with Random Forest classifier.
- Universal feature set achieves about 93% F-measure across datasets.
- Selected features are effective without relying on third-party services.

## Abstract

Phishing as one of the most well-known cybercrime activities is a deception of online users to steal their personal or confidential information by impersonating a legitimate website. Several machine learning-based strategies have been proposed to detect phishing websites. These techniques are dependent on the features extracted from the website samples. However, few studies have actually considered efficient feature selection for detecting phishing attacks. In this work, we investigate an agreement on the definitive features which should be used in phishing detection. We apply Fuzzy Rough Set (FRS) theory as a tool to select most effective features from three benchmarked data sets. The selected features are fed into three often used classifiers for phishing detection. To evaluate the FRS feature selection in developing a generalizable phishing detection, the classifiers are trained by a separate out-of-sample data set of 14,000 website samples. The maximum F-measure gained by FRS feature selection is 95% using Random Forest classification. Also, there are 9 universal features selected by FRS over all the three data sets. The F-measure value using this universal feature set is approximately 93% which is a comparable result in contrast to the FRS performance. Since the universal feature set contains no features from third-part services, this finding implies that with no inquiry from external sources, we can gain a faster phishing detection which is also robust toward zero-day attacks.