Fraudulent SMS messages and spam attacks have become a major cybersecurity concern due to the rapid growth of mobile communication and digital services. Traditional filtering systems often fail to identify evolving spam patterns, phishing links, and deceptive text messages used in financial fraud and identity theft. This paper presents a Machine Learning (ML)-based Fraud SMS Spam Detection framework capable of automatically classifying messages as spam or legitimate (ham). A structured review of existing ML and Deep Learning approaches is performed, analysing datasets, preprocessing techniques, feature extraction methods, model architectures, and evaluation metrics. The study proposes a comparative framework using Naive Bayes, Support Vector Machine (SVM), Random Forest, Logistic Regression, and Long Short-Term Memory (LSTM) models. The framework focuses on improving detection accuracy, reducing false positives, and enabling real-time spam filtering. The proposed system aims to support secure mobile communication by providing an intelligent and scalable SMS spam detection mechanism.
S et al. (Tue,) studied this question.