PhishCatcher Client-Side Defense Against Web Spoofing Attacks Using Machine Learning

Phishing attacks have become one of the most significant cybersecurity threats, where attackers create fraudulent websites to device users and steal sensitive information such as login credentials and financial data. Traditional detection techniques, such as blacklist-based approaches ,are ineffective against newly generated phishing websites and lack real-time protection. This paper presents PhishCatcher, a client-side defense mechanism that utilizes machine learning techniques to detect web spoofing attacks efficiently. The proposed system extracts multiple features from websites, including URL characteristics, domain information and webpage content, and applies a Random Forest classifier to identify malicious websites. The system is implemented as a browser extension, enabling real- time detection and user alerts without relying on server-side processing. Experimental results demonstrate that the proposed model achieves high accuracy, low latency, and improved detection performance compared to conventional methods. The solution enhances user security and provides an effective approach to mitigate phishing attacks in modern web environments.