Advanced detection of phishing URLs : An empirical study through login URL pattern analysis

Phishing attacks pose critical cybersecurity challenges, demanding robust detection methods. This study presents a novel hybrid model combining Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks for detecting phishing URLs. Leveraging a Kaggle dataset, the research evaluates the performance of CNN, LSTM, and a hybrid CNN-LSTM architecture. The hybrid approach uniquely integrates CNN’s feature extraction capabilities with LSTM’s sequence learning strength, delivering enhanced detection accuracy and reliability. Experimental results underscore its effectiveness in distinguishing phishing and legitimate URLs, providing a significant advancement in phishing detection technologies and addressing the growing need for innovative cyber defence mechanisms.