DETECTION AND CLASSIFICATION ANDROID MALWARE BY XGBOOST MODEL

Abstract

The Android operating system is one of the most widely used platforms on smart devices worldwide, making it a prime target for malware attacks. With the increasing complexity and frequency of security threats, there is a pressing need to adopt advanced analysis techniques to enhance the security of this system. In this context, the importance of malware analysis through static, dynamic, and hybrid methods becomes evident, along with the integration of artificial intelligence techniques particularly machine learning for early and accurate detection. The Kronodroid dataset, one of the largest specialized databases in this field, was used to train and test a machine learning model based on the XGBoost algorithm. The adopted methodology includes steps such as data acquisition, preprocessing, and feature selection before applying the model. The study concluded that the use of machine learning especially when combined with hybrid analysis of software effectively enhances the ability of cybersecurity systems to detect Malware software and accurately understand its behavior, thereby supporting the development of more efficient preventive solutions for the Android platform.