Abstract
The rapid expansion of Android devices has increased exposure to evolving cybersecurity threats, particularly malware. Traditional single-model detection techniques often struggle to maintain high accuracy due to the diverse and sophisticated nature of modern attacks. This study proposes an optimal ensemble learning approach for automated Android malware detection, integrating multiple machine learning classifiers to enhance robustness, precision, and adaptability. By combining features extracted from application permissions, API calls, behavioral patterns, and static code attributes, the ensemble model mitigates individual classifier limitations and improves overall detection performance. Experimental results demonstrate that the proposed framework outperforms conventional standalone models in terms of accuracy, recall, and false-positive reduction. This approach offers a scalable and reliable solution for strengthening mobile cybersecurity and protecting users against emerging Android malware threats.