Smishing Detection: Combating SMS Phishing Attacks by Utilizing Machine-Learning Algorithms

With the rapid uptake of mobile communications, cybercriminals have increasingly resorted to using SMS (Short Message Services) in the guise of phishing attacks commonly referred to as smishing (SMS phishing). Phishing SMS messages impersonate trusted organizations to persuade users into clicking malicious links, providing personal credentials, or installing malware. This paper reviews up-to-date advancements in machine learning for smishing detection, using insights derived from various studies on the subject. It looks into critical machine learning models such as Deep Learning models (CNN, LSTM), Logistic Regression, Random Forest, Support Vector Machines (SVM), and Gradient Boosting,) to classify messages as spam, phishing, or legitimate. It examines feature extraction techniques such as TF-IDF, N-grams, and natural language processing (NLP) in the hope of improving detection accuracy. In this way, it also looks at how cyber threat intelligence and real-world datasets such as SpamAssassin, the UCI Machine Learning Repository, and PhishTank can be used to build strong models. The results show that ensemble learning and hybrid deep learning techniques are better at finding things than traditional methods, and they do this without increasing the number of false positives. Challenges such as adversarial SMS attacks, multilingual phishing messages, and real-time detection limitations remain plausible. Future works need to look into adaptability to real-time models, CTI-based threat analysis, and understandable AI (XAI) detection transparency. Applying machine learning-driven smishing detection brings up the overall solution's intelligent automated approach and adaptive defense mechanisms against mobile phone phishing threats evolving, resulting in increased security for mobiles and, hence, their users.