Exploring the Potential of Convolutional Neural Networks for Phishing URL Detection in Cybersecurity

Abstract

Phishing attacks continue to pose one of the most significant cybersecurity threats by exploiting deceptive websites and malicious URLs to obtain sensitive personal and organizational information. As phishing techniques become increasingly sophisticated, accurate and automated detection methods are essential for enhancing cybersecurity protection. This study investigates the potential of Convolutional Neural Networks (CNNs) for phishing URL detection by leveraging their capability to automatically extract discriminative features from sequential textual data.The proposed approach incorporates data preprocessing and hyperparameter optimization to improve the performance of the CNN-based classification model. The model was trained and evaluated using a dataset containing both phishing and legitimate URLs. Experimental results demonstrate that the proposed model achieved a classification accuracy of 85.42%, indicating that CNNs provide an effective approach for distinguishing phishing URLs from legitimate ones. The findings suggest that deep learning techniques, particularly CNNs, can enhance automated phishing detection while reducing the need for manual feature engineering. This study contributes to the development of intelligent cybersecurity solutions and provides a foundation for future research on improving phishing detection through advanced deep learning architectures and optimization techniques.