Abstract
The growing popularity of Android devices and their use for storing personal and sensitive information have made them a major target for malware attacks, leading to serious privacy and security risks. Therefore, an effective malware detection method is essential. This study proposes a framework for Android malware detection by combining machine learning techniques with Genetic Algorithm (GA)-based feature selection. Machine learning helps identify malicious applications by analyzing patterns in application data. However, the performance of these models depends on selecting the most relevant features. To improve this, a Genetic Algorithm is used to select the most useful features and remove irrelevant or redundant ones. Both static and dynamic features, such as permissions, API calls, and network behavior, are extracted from Android applications. The optimized feature set is then used to train machine learning models, including Random Forest, Support Vector Machine, and Artificial Neural Network. Experimental results show that GA-based feature selection improves detection performance, achieving higher accuracy, precision, recall, and F1-score. This approach provides an efficient and reliable solution for enhancing Android malware detection and improving mobile security.