Deep learning in phishing mitigation: a uniform resource locator-based predictive model

Abstract

To mitigate the evolution of phish websites, various phishing prediction8 schemes are being optimized eventually. However, the optimized methods produce gratuitous performance overhead due to the limited exploration of advanced phishing cues. Thus, a phishing uniform resource locator-based predictive model is enhanced by this work to defeat this deficiency using deep learning algorithms. This model’s architecture encompasses pre-processing of the effective feature space that is made up of 60 mutual uniform resource locator (URL) phishing features, and a dual deep learning-based model of convolution neural network with bi-directional long short-term memory (CNN-BiLSTM). The proposed predictive model is trained and tested on a dataset of 14,000 phish URLs and 28,074 legitimate URLs. Experimentally, the performance outputs are remarked with a 0.01% false positive rate (FPR) and 99.27% testing accuracy.