Lightweight Mobile Malware Detection Using Permission-Based Static Analysis

The increasing usage of mobile devices has significantly expanded the Android application ecosystem, making it an attractive target for malware attacks. Traditional signature-based detection techniques are ineffective against newly emerging and obfuscated malware. This paper presents a lightweight mobile malware detection approach based on static analysis of Android applications. The proposed system extracts permission-based features from application packages and employs machine learning classification techniques to distinguish between benign and malicious applications. Experimental evaluation demonstrates that the proposed approach achieves reliable detection accuracy with minimal computational overhead. The results indicate that permission-based static analysis can serve as an effective solution for mobile malware detection in resource-constrained environments.