SMS Guard: Enhancing Spam Detection using Multinomial Naive Bayes for Secure Communication

This research study presents a robust spam detection system, SMS Guard, that leverages the Multinomial Naive Bayes algorithm to classify SMS messages as either spam or ham. With the increasing volume of SMS traffic, spam messages have become a significant threat to users, leading to privacy breaches and online fraud. The proposed model is trained on a labeled dataset containing both legitimate (ham) and spam messages. Through efficient preprocessing techniques, such as tokenization and normalization, the model achieves high accuracy and precision in detecting spam messages. By evaluating the system's performance using metrics like F1 score, this paper demonstrates the effectiveness of the model in providing a reliable solution for real-time spam detection, enhancing user security in digital communication.