Machine Learning Based Approaches For Android Malware Detection using Hybrid Feature Analysis

Smart Phones have become an integral part of our lives, offering a wide range of functionalities and services. However, as the popularity of Android has grown, so has the threat of malware attacks targeting these devices. The increasing number of mobile applications and the significant amount of personal and sensitive information stored on smartphones make them lucrative targets for malicious actors. It is crucial to develop effective methods to identify and mitigate these threats to ensure the security and privacy of Android users. This paper presents a comparitive study of different machine learning approaches for binary classification (malicious and benign) of Android applications, based on Hybrid feature analysis (static and dynamic). Also it conducts a comparative analysis of the highest results to other relevant studies. Experimental evaluations results reach 98% accuracy in detecting malicious applications.