Survey of Optimization Techniques for Phishing Website Detection

Phishing is one of the critical threats that persist in the realm of cybersecurity, as it preys on unsuspecting users and entities to harvest sensitive information, such as financial accounts, passwords, and personally identifiable information. Recurrent development of more elaborate phishing strategies raises the need for new automatic detection systems. Optimization algorithms like swarm intelligence, evolutionary algorithms, and other methods based on nature have been used all over the place to make phishing detection systems work better. This research presents a systematic study and classification of phishing website detection techniques using optimization algorithms. This paper summarizes 18 studies and shows how these optimization algorithms can help with better feature selection, better classification performance, and problems like low efficiency and uncertain convergence. In the long run of this study, I emphasize the importance of these techniques in overcoming issues that affect the accuracy, sensitivity, and efficiency of the existing phishing detection systems. In addition, this work identifies existing gaps and provides recommendations for future studies to create an intelligent system that is well adaptable and scalable for everincreasing phishing attempts.