A Transformer-based Model to Detect Phishing URLs

TL;DR

This paper introduces a transformer-based model for detecting phishing URLs that significantly outperforms existing methods, achieving 97.3% accuracy and demonstrating robustness against evolving attack tactics.

Contribution

The paper presents a novel transformer-based approach for phishing URL detection that surpasses classical models in accuracy and robustness.

Findings

Achieves 97.3% detection accuracy

Outperforms six classical detection models

Demonstrates robustness against evolving phishing tactics

Abstract

Phishing attacks are among emerging security issues that recently draws significant attention in the cyber security community. There are numerous existing approaches for phishing URL detection. However, malicious URL detection is still a research hotspot because attackers can bypass newly introduced detection mechanisms by changing their tactics. This paper will introduce a transformer-based malicious URL detection model, which has significant accuracy and outperforms current detection methods. We conduct experiments and compare them with six existing classical detection models. Experiments demonstrate that our transformer-based model is the best performing model from all perspectives among the seven models and achieves 97.3 % of detection accuracy.