Machine Learning for Mobile Defense: Detecting SMS Malware and Riskware on Android

Android smartphones are frequently targeted by SMS Malware and Riskware attacks that aim to steal private information such as user credentials, photos, videos, and banking details. Often, Android users unknowingly allow these attacks by clicking on unknown links or messages. The goal of this research paper is to boost user confidence and privacy on Android devices. The CICMalDroid 2020 dataset, which includes data on traffic patterns related to Riskware and SMS malware attacks, forms the basis of this research. The study introduces a methodology for the early detection of these threats by incorporating a machine learning-enabled chip at the hardware level. The dataset has been processed using various machine learning algorithms to assess the most effective ones for detecting Android malware. The findings demonstrate the superiority of the random forest algorithm on the CICMalDroid dataset, with this classifier achieving the highest accuracy, recall, and F1 score compared to others. Conversely, the Naive Bayes method is noted for its reliability and its ability to minimize false positives. These outcomes emphasize the importance of strengthening cybersecurity measures, regularly updating software, and the critical role of machine learning in enhancing the security of Android devices.