The Impact of SMS Phishing using Machine Learning Classifiers with Innovative Techniques
Anisha Asirvatham, C. Meenakshi · Procedia Computer Science · 2025
These days, machine learning has an amazing ability to present the results efficiently. Network technology computing systems have long served as a critical framework to supply machine learning with deterministic computing resources. This technique can be advantageous to networking. The application of machine learning in detection of phishing of SMS in a network is the main topic of this article. This not only stimulates new network applications but also aids in the resolution of certain obsolete network issues. The fundamental approach to describe how machine learning technology works in network model is summarized in this article. The SMS spam can be detected using the proposed system, where the feature extraction can be done using stemming and the different machine learning classifiers are used to evaluate the accuracy of the proposed system. The different machine learning classifiers used in this system are Logistic regression, linear regression, K Nearest Neighbors and Naïve Bayes. The new system SpamSMS is the ensemble method using Naïve Bayes and Stacking Algorithm which gives the maximum accuracy towards the provided dataset to check for the spam messages.