Integrated Android Malware Detection System Using Static and Dynamic Analysis Techniques

Objective: To develop and validate an automated tool for detecting Android malware using combined static and dynamic analysis methods.

Mobile malware is a growing threat in India, impacting millions of Android users and organizations who rely on smartphones for banking, e-governance, and business operations. Attackers increasingly exploit app vulnerabilities to steal data, track users, or disrupt services, causing financial and privacy losses.

This project proposes an engineering solution—a hybrid malware detection system that analyzes Android APK files via static code inspection and dynamic behavioral monitoring. The tool integrates open-source frameworks, machine learning, and sandboxing to identify malicious patterns in both code and runtime activity.

Key features include APK analysis, permission mapping, code signature extraction, dynamic execution in a controlled sandbox, behavioral anomaly detection, and a user-friendly dashboard for result visualization. The working model is demonstrated with real Android malware samples from public datasets and validated against benign apps.

Industry and societal impact: The system can be deployed for enterprise app vetting, digital forensics, and national CERTs, helping secure India's mobile ecosystem. The scalable architecture allows future integration with threat intelligence feeds and adaptation for evolving malware techniques.