Deep Learning for Phishing URL Detection: A Comparative Analysis of CNN and RNN Models for Enhanced Cybersecurity

Abstract

Phishing remains a persistent ever-changing threat to cybersecurity, thus demanding the invention of intelligent and scalable detection algorithms. The study here examines the ability of deep learning methodologies, viz., Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN), in the detection of phishing Uniform Resource Locator (URL). Accurately detecting malicious URLs is tackled by this research through a systematic technique of data preprocessing, tokenization, and sequence padding. Experimental results demonstrate that the CNN model performs reasonably well, with an accuracy of 84.56%, recall of 72.19%, precision of 95.43%, and F1score of 82.20%, whereas the RNN model, with an accuracy of 91.56%, recall of 89.46%, precision of 93.17%, and F1-score of 91.28%, outperforms the CNN model. This evidently suggests that RNN is stronger in capturing the sequential patterns embedded in URLs and thus working better in phishing detection. This study exemplifies the promise of deep learning approaches towards making cyber security more robust and serves as a stepping stone for future research in hybrid models and real-time detection.