Android Malware Detection: an Eigenspace Analysis Approach

TL;DR

This paper presents a machine learning approach using eigenspace analysis for Android malware detection, achieving high accuracy with low false positives based on static analysis features.

Contribution

It introduces a novel eigenspace analysis method for Android malware detection that improves accuracy over existing static analysis techniques.

Findings

Detection rate over 96%

Low false positive rate

Effective on real malware samples

Abstract

The battle to mitigate Android malware has become more critical with the emergence of new strains incorporating increasingly sophisticated evasion techniques, in turn necessitating more advanced detection capabilities. Hence, in this paper we propose and evaluate a machine learning based approach based on eigenspace analysis for Android malware detection using features derived from static analysis characterization of Android applications. Empirical evaluation with a dataset of real malware and benign samples show that detection rate of over 96% with a very low false positive rate is achievable using the proposed method.