Email Spam Detection Using Hierarchical Attention Hybrid Deep Learning Method

TL;DR

This paper introduces a novel email spam detection method combining convolutional neural networks, gated recurrent units, and attention mechanisms, achieving superior performance through hierarchical feature extraction and cross-dataset evaluation.

Contribution

It presents a new hybrid deep learning model with hierarchical convolutional features and attention, improving spam detection accuracy over existing methods.

Findings

Outperforms state-of-the-art attention-based models

Effective cross-dataset evaluation demonstrates robustness

Hierarchical convolution enhances feature extraction

Abstract

Email is one of the most widely used ways to communicate, with millions of people and businesses relying on it to communicate and share knowledge and information on a daily basis. Nevertheless, the rise in email users has occurred a dramatic increase in spam emails in recent years. Processing and managing emails properly for individuals and companies are getting increasingly difficult. This article proposes a novel technique for email spam detection that is based on a combination of convolutional neural networks, gated recurrent units, and attention mechanisms. During system training, the network is selectively focused on necessary parts of the email text. The usage of convolution layers to extract more meaningful, abstract, and generalizable features by hierarchical representation is the major contribution of this study. Additionally, this contribution incorporates cross-dataset evaluation, which enables the generation of more independent performance results from the model's training dataset. According to cross-dataset evaluation results, the proposed technique advances the results of the present attention-based techniques by utilizing temporal convolutions, which give us more flexible receptive field sizes are utilized. The suggested technique's findings are compared to those of state-of-the-art models and show that our approach outperforms them.