Android Malware Detection: A Machine Leaning Approach

TL;DR

This paper evaluates various machine learning models for Android malware detection, highlighting ensemble methods as the most effective, while discussing trade-offs in interpretability and efficiency for practical deployment.

Contribution

It provides a comparative analysis of multiple ML techniques for Android malware detection, emphasizing the effectiveness of ensemble methods and practical considerations.

Findings

Ensemble methods outperform individual models in accuracy.

Trade-offs exist between model interpretability, efficiency, and accuracy.

The study offers insights for deploying ML-based malware detection in real-world scenarios.

Abstract

This study examines machine learning techniques like Decision Trees, Support Vector Machines, Logistic Regression, Neural Networks, and ensemble methods to detect Android malware. The study evaluates these models on a dataset of Android applications and analyzes their accuracy, efficiency, and real-world applicability. Key findings show that ensemble methods demonstrate superior performance, but there are trade-offs between model interpretability, efficiency, and accuracy. Given its increasing threat, the insights guide future research and practical use of ML to combat Android malware.