Advancements of SMS Spam Detection: A Comprehensive Survey of NLP and ML Techniques

Abstract

In the digital age, the ubiquity of text messaging has unfortunately paved the way for SMS phishing, or 'smishing,' a deceptive practice where fraudsters dispatch fraudulent messages to extract sensitive information from unsuspecting recipients. This issue is not trivial. It represents a significant threat to both personal privacy and organizational security, leading to potential data breaches and financial repercussions. Against this backdrop, the imperative for advanced detection strategies is undeniable. This survey leverages a systematic review methodology to assess the effectiveness of Natural Language Processing (NLP) and Machine Learning (ML) techniques in the detection of SMS phishing, also known as smishing. By methodically analyzing research spanning various detection strategies, the study illuminates the evolution from basic rule-based frameworks to sophisticated ML algorithms, enriched with NLP for deep analysis. The findings underscore the superior efficacy of combining ML classifiers with NLP, particularly through the deployment of advanced deep learning models like Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), which offer unprecedented accuracy in identifying and thwarting complex smishing attacks. The value of this study lies in its comprehensive synthesis of current methodologies and its contribution to the ongoing enhancement of cybersecurity defenses. It serves as a crucial guide for future research directions, emphasizing the necessity of adopting and innovating cutting-edge NLP and ML techniques to stay ahead of evolving digital threats.

Topics & Concepts