PHISH CATCHER CLIENT-SIDE DEFENCE AGAINST WEB SPOOFING ATTACKS USING MACHINE LEARNING

Abstract

Web spoofing attacks, such as phishing and malicious imitation of legitimate websites, pose a significant threat to online users by stealing sensitive information like credentials and financial data. Traditional server-side detection methods often fail to protect users in real-time before interaction with spoofed sites. This paper proposes Phish Catcher, a client-side defense mechanism that leverages machine learning techniques to detect and prevent web spoofing attacks proactively. The system analyzes features extracted from URLs, webpage content, and website behavior to classify sites as legitimate or malicious. By implementing real-time monitoring on the client side, Phish Catcher provides immediate alerts, reducing the risk of credential compromise. Experimental results demonstrate that the proposed approach achieves high accuracy and low false-positive rates, outperforming existing client-side anti-phishing tools. This approach emphasizes usercentric security, enabling safer web browsing without relying solely on server-based detection.