The applicability of a hybrid framework for automated phishing detection

Phishing attacks are a critical and escalating cybersecurity threat in the modern digital landscape. As cybercriminals continually adapt their techniques, automated phishing detection systems have become essential for safeguarding Internet users. However, many current systems rely on single-analysis models, making them vulnerable to sophisticated bypass attempts by hackers. This research delves into the potential of hybrid approaches, which combine multiple models to enhance both the robustness and effectiveness of phishing detection. It highlights existing hybrid models' limitations that focus primarily on effectiveness while ignoring broader applicability. To address these gaps, we introduce a novel framework explicitly designed for applicability in the real world, which poses the foundation for practical and robust phishing detection architectures. We develop a proof of concept to evaluate its effectiveness, robustness, and detection speed. Additionally, we introduce an innovative methodology for simulating bypass attacks on single-analysis base models. Our experiments demonstrate that the proposed hybrid framework outperforms individual models, displaying higher effectiveness, robustness against bypassing attempts, and real-time detection capabilities. Our proof of concept achieves an accuracy of 97.44% thereby outperforming the current state-of-the-art approach while requiring less computational time. The results provide insights into the multifaceted factors of hybrid models, extending beyond mere effectiveness, and emphasize the importance of holistic applicability in hybrid approaches to address the critical need for robust defenses against phishing attacks.