Abstract :

Android Malware Has Become A Significant Threat Due To The Rapid Growth Of Mobile Applications And The Limitations Of Traditional Signature-based Detection Methods In Identifying Unknown Attacks. This Paper Proposes An Efficient Android Malware Detection System Using Machine Learning Combined With Genetic Algorithm–based Feature Selection. Android Applications (APKs) Are Reverse Engineered To Extract Static Features Such As Permissions And Application Components From The AndroidManifest.xml File Using Tools Like Androguard. The Extracted Features Are Transformed Into Feature Vectors And Optimized Using A Genetic Algorithm To Reduce Dimensionality And Improve Classification Performance. The Optimized Feature Set Is Then Used To Train Machine Learning Models, Including Support Vector Machine (SVM) And Artificial Neural Network (ANN), For Accurate Classification Of Malware And Goodware. Experimental Analysis Demonstrates That The Proposed Approach Achieves High Detection Accuracy While Reducing Computational Complexity. The System Is Also Capable Of Identifying Previously Unseen Malware Variants, Making It A Reliable And Scalable Solution For Enhancing Android Security.

Published:

26-5-2026

Issue:

Vol. 26 No. 5 (2026)

Page Nos:

1886-1895

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite