Hybrid Phishing Detection Based on Automated Feature Selection Using the Chaotic Dragonfly Algorithm

Due to the increased frequency of phishing attacks, network security has gained attention researchers. In addition this, large volumes data are created every day, and these include inappropriate unrelated features that influence accuracy machine learning. There is therefore a need for robust method detecting threats improving detection accuracy. this study, three classifiers were applied improve algorithm: decision tree, k-nearest neighbors (KNN), support vector (SVM). Selecting relevant improves target class determines label with greatest probability. The proposed work clearly describes how feature selection using Chaotic Dragonfly Algorithm provides more accurate results than all other baseline classifiers. It also indicates appropriate classifier be when websites. Three publicly available datasets used evaluate method. They reliable training model measuring prediction