High Precision Screening for Android Malware with Dimensionality Reduction
Authors:
- Britton WolfeBWBritton Wolfe
- Karim ElishKEKarim Elish
- Danfeng YaoDYDanfeng Yao
- 1 December 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 21-28
Abstract
We present a new method of classifying previously unseen Android applications as malware or benign. The algorithm starts with a large set of features: the frequencies of all possible n-byte sequences in the application's byte code. Principal components analysis is applied to that frequency matrix in order to reduce it to a low-dimensional representation, which is then fed into any of several classification algorithms. We utilize the implicitly restarted Lanczos bidiagonalization algorithm and exploit the sparsity of the n-gram frequency matrix in order to efficiently compute the low-dimensional representation. When trained upon that low-dimensional representation, several classification algorithms achieve higher accuracy than previous work.Keywords
This publication has 17 references indexed in Scilit:
- Comprehensive Behavior Profiling for Proactive Android Malware Detection2014
- Applying machine learning classifiers to dynamic Android malware detection at scale2013
- Retargeting Android applications to Java bytecode2012
- Using probabilistic generative models for ranking risks of Android apps2012
- DroidMat: Android Malware Detection through Manifest and API Calls Tracing2012
- Crowdroid2011
- “Andromaly”: a behavioral malware detection framework for android devicesJournal of Intelligent Information Systems, 2011
- Static Analysis of Executables for Collaborative Malware Detection on Android2009
- Detection of malicious code by applying machine learning classifiers on static features: A state-of-the-art surveyInformation Security Technical Report, 2009
- Analysis of a complex of statistical variables into principal components.Journal of Educational Psychology, 1933