Published Paper Details:

In the evolving landscape of cyber security threats, web spoofing attacks persist as a significant challenge, exploiting user trust in web interfaces. Phishing emails, alluring adverts, click jacking, malware, spoofing injection, session hijacking, man-in-the-middle, denial of service, and cross-site scripting assaults are the techniques used to deceive a user into visiting a website. As web spoofing attacks continue to pose a significant threat to online security, there is an urgent need for robust and efficient mechanisms to detect and prevent such fraudulent activities. The proposed system employs a sophisticated feature extraction mechanism to analyze various aspects of web pages, including visual elements, structural components, and behavioral patterns. The Convolutional Neural Network (CNN) is chosen for its ability to handle complex and non-linear relationships within the dataset, providing a reliable and adaptable solution for phishing detection. By training the model on a diverse set of legitimate and phishing websites, the phish catcher gains the capability to recognize subtle and evolving attack strategies. The system operates on the client- side, ensuring real-time protection without relying solely on server-side defenses.