Enhancing Phishing Detection in Sulu, Philippines: A Machine Learning Approach to Combat Evolving Cyber Threats

Abstract

Phishing attacks are a growing threat to individuals and organizations worldwide, and Sulu, Philippines, is no exception. These attacks use deceptive emails, websites, and text messages to trick victims into revealing sensitive information such as login credentials, financial data, and personal details. Machine learning (ML) techniques have emerged as a promising solution for enhancing phishing detection due to their ability to learn patterns and adapt to new threats. This study investigates the effectiveness of ML approaches in enhancing phishing detection in Sulu, Philippines. A comprehensive dataset of phishing and legitimate websites was collected, incorporating features relevant to Sulu's context, such as local e-commerce platforms, government services, and banking institutions. Various ML algorithms, including Random Forest, Support Vector Machine, and Naive Bayes, were trained and evaluated on this dataset. The ML models demonstrated high accuracy in detecting phishing websites. The Random Forest model achieved the highest accuracy of 98.7%, followed by the Support Vector Machine with 96.5% accuracy and the Naive Bayes with 94.2% accuracy. Feature importance analysis revealed that specific features, such as URL structure, domain age, and the presence of login forms, played a crucial role in accurate classification. In conclusion, the findings suggest that ML techniques can significantly enhance phishing detection capabilities in Sulu, Philippines. Implementing these techniques in security solutions can help protect individuals and organizations from falling victim to phishing attacks.