What question did this study set out to answer?

The aim is to enhance malware detection accuracy and robustness for Android applications using machine learning techniques.

April 13, 2026Open Access

Automated Android Malware Detection Using Optimal Ensemble Learning Approach for Cyber Security

Key Points

The aim is to enhance malware detection accuracy and robustness for Android applications using machine learning techniques.
Developed an automated detection system for Android malware.
Analyzed behavioral and static features of applications.
Utilized ensemble learning with models such as Random Forest and Neural Networks.
Applied data preprocessing and feature selection methods to improve data quality.
Evaluated performance using accuracy, precision, recall, and F1-score.
Ensemble learning approach showed higher detection accuracy compared to individual models.
The system effectively detected both known and unknown malware.
Achieved reduced false positives and better generalization in malware detection.

Abstract

The rapid growth of Android devices and applications has significantly increased the risk of malware attacks, making mobile security a critical concern in today’s digital landscape. Traditional signature-based malware detection techniques are often ineffective against newly emerging and evolving threats, as they rely on known patterns and fail to detect zero-day attacks. This project proposes an Automated Android Malware Detection System using an Optimal Ensemble Learning Approach to enhance detection accuracy and robustness in cybersecurity applications. The system aims to identify malicious applications by analyzing their behavioral and static features using advanced machine learning techniques. The proposed methodology involves collecting Android application datasets and extracting relevant features such as permissions, API calls, and system behaviors. Data preprocessing techniques are applied to remove noise and handle missing values, followed by feature selection methods to identify the most significant attributes influencing malware detection. The system employs an ensemble learning approach, combining multiple machine learning models such as Random Forest, Support Vector Machines, Gradient Boosting, and Neural Networks. The optimal ensemble model is created by selecting and combining classifiers based on performance metrics, thereby improving overall prediction accuracy and reducing false positives. The performance of the system is evaluated using metrics such as accuracy, precision, recall, and F1-score. Experimental results demonstrate that the ensemble learning approach outperforms individual models by providing higher detection accuracy and better generalization. The system is capable of detecting both known and unknown malware, making it suitable for real-time cybersecurity applications. Additionally, the automated nature of the system reduces human intervention and enhances scalability. Overall, this project highlights the effectiveness of ensemble learning techniques in strengthening Android malware detection and improving mobile security against evolving cyber threats.

Read Full Paperexternally

اسأل الذكاء الاصطناعي

Bookmark

View Full Paper