Modelling an Efficient Approach to Analyse Clone Phishing and Predict Cyber-Crimes

Abstract

Clone phishing is one of the most common social engineering attacks that organizations, governments, and the general public have to deal with. The threat posed by clone emails has increased dramatically over the past few years and necessitates the development of an appropriate clone detection system. To combat this threat, this research study utilizes machine learning strategies to predict clone phishing by detecting clone emails. This article discusses the deep learning-based clone phishing prevention prototype, a multi-modal deep neural network (DNet) to recognize and avoid clone phishing attacks. The database is split to train the detection model and then use test data to confirm the findings in order to collect inherent characteristics of the email text and other parameters that can be classified as clone and non-clone. While comparing the proposed model with the other existing techniques, the results show that the proposed DNet model is comparatively more accurate and successful.