Efficient Malware Detection in Android Devices to Improve Cyber Security

Abstract

The project introduces a novel framework for detecting Android malware based on permissions, utilizing multiple linear regression methods. Permissions play a crucial role in the security of the Android operating system, serving as fundamental indicators of an application's behavior. Through static analysis, the framework extracts application permissions and employs machine learning techniques to conduct security analyses. Specifically, the framework employs multiple linear regression techniques to develop two classifiers for permission-based Android malware detection. These classifiers leverage the relationships between various permission attributes to accurately identify potentially malicious applications. Notably, the framework achieves notable performance levels using classification algorithms without the need for overly complex models. In the project, the existing system utilizes the Random Forest (RF) algorithm, while the proposed system adopts the Support Vector Machine (SVM) algorithm. Both algorithms are evaluated in terms of accuracy, with the results demonstrating that the proposed SVM approach outperforms the existing RF method. This highlights the effectiveness of SVM in accurately detecting Android malware based on permission analysis.