Training Neural Networks by Enhance Grasshopper Optimization Algorithm for Spam Detection System

Abstract

A significant negative impact of spam e-mail is not limited only to the serious waste of resources, time, and efforts, but also increases communications overload and cybercrime. Perhaps the most damaging aspect of spam email is that it has become such a major tool for attacks of cross-site scripting, malware infection, phishing, and cross-site request forgery, etc. Due to the nature of the adaptive unsolicited spam, it has been weakening the effect of the previous discovery techniques. This article proposes a new Spam Detection System (SDS) framework, by using a series of six different variants of enhanced Grasshopper Optimization Algorithm (EGOAs), which are investigated and combined with a Multilayer Perceptron (MLP) for the purpose of advanced spam email detection. In this context, the combination of MLP and EGOAs produces Neural Network (NN) models, referred to (EGOAMLPs). The main idea of this research is to use EGOAs to train the MLP to classify the emails as spam and non-spam. These models are applied to SpamBase, SpamAssassin, and UK-2011 Webspam benchmark datasets. In this way, the effectiveness of our models on detecting diverse forms of spam email is evidenced. The results showed that the proposed MLP model trained by EGOAs achieves a higher performance compared to other optimization methods in terms of accuracy, detection rate, and false alarm rate.