Phishing URLs Detection Method Using Hybrid Feature and Convolutional Neural Networks with Attention Mechanisms

In this study, we introduce a novel method for phishing URL detection, combining hybrid features with convolutional neural networks (CNNs) enhanced by attention mechanisms. These hybrid features are extracted using word2vec, principal component analysis (PCA), and natural language processing (NLP), offering a comprehensive representation of URL data. The CNNs, renowned for their feature extraction capabilities, are further refined with attention mechanisms, allowing the model to focus on the most informative parts of the URL during training. This approach significantly enhances the model’s performance and robustness against phishing threats. Tested on a custom dataset, our method achieved an impressive accuracy of 99.83%, surpassing existing techniques and demonstrating potential for real-time application in diverse web environments. The results highlight our method’s scalability and efficiency, marking a significant advancement in cyber security and phishing detection technologies.