Harnessing ML and NLP for Enhanced Cybersecurity: A Comprehensive Approach for Phishing Email Detection

Abstract

Emails stand as a predominant mode of online communication, facilitating the exchange of information. With the ubiquity of emails, there has been a marked rise in unsolicited messages, particularly phishing emails. These deceptive emails aim to mislead recipients, often masquerading as trustworthy entities, to extract confidential information. Embedded with dubious offers, advertisements, malicious links, malware, and trojans, perpetrators deploy these emails with malicious intent, primarily to commit fraud. Consequently, distinguishing between phishing attempts and genuine emails becomes paramount. This study constructs machine learning-based models to detect phishing emails, ensuring accurate discernment between genuine and fraudulent messages. Leveraging two datasets, the Fraud Email Dataset and the Phishing Email Dataset, we developed and evaluated classifiers, including Logistic Regression, Decision Tree, Random Forest, and SVM. The Random Forest model emerged as the most effective, achieving accuracies of 98.72% on the Fraud Email Dataset and 99.15% on the Phishing Email Dataset, demonstrating strong generalizability across diverse phishing patterns. These results underscore the efficacy of ensemble methods for enhancing cybersecurity by reliably detecting phishing emails.