Abstract
Mobile devices have become an integral part of daily human activities. The rapid growth and impact of these devices have made them increasingly susceptible to cyber-attacks. Attackers often exploit Short Text Messages (SMS) to target smartphone users. Smishing, also known as SMS phishing, is a type of attack that targets smartphone users through text messages. Smishing, a type of phishing, differs from traditional phishing in several ways, such as the information available in the SMS and the attack strategy. As such, detecting smishing is challenging because attackers share minimal information. The research explores the risks of smishing and vishing attacks targeting mobile device users. To tackle this, machine learning algorithms were developed to detect smishing attacks and a blacklist to identify potential vishing attacks. The models evaluated in this study include the Naïve Bayes, Decision Tree, and Random Forest algorithms. The results obtained indicated that the Random Forest model performed best in the selected environment. When addressing vishing attacks, the prototype solely relied on a blacklist which can be valuable, but its effectiveness is reliant on continuous updates and monitoring.