This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License
|
||||||||
|
Paper Details
Paper Title
Automated Malicious Android App Detection using Machine Learning Methods
Authors
  Tendai Munyaradzi Marengereke,  K. Sornalakshmi
Abstract
There has exponential been growth of mobile computing, and as the capabilities of smartphones has increased so have malware threats. Enterprises and individual users have extensively adopted the use of Android mobile devices, users can download apps from unofficial marketplaces which pose a security risk. We overview Android malware detection methods and showcase an architecture for a malware detection system as an in-cloud service. The architecture uses automated static methods to decompile apk source code and then utilizes machine learning methods to classify risky, malicious and benign apps according to permissions requested, and installation origin. We present our system and experimental results on a dataset of 300 malware and 500 benign application. Our trained model provides an accuracy detection rate after evaluation of 89%.
Keywords- Android, Malware Detection, Classification, Machine Learning, Data Mining, Cloud Offloading.
Publication Details
Unique Identification Number - IJEDR1502035Page Number(s) - 191-197Pubished in - Volume 3 | Issue 2 | May 2015DOI (Digital Object Identifier) -    Publisher - IJEDR (ISSN - 2321-9939)
Cite this Article
  Tendai Munyaradzi Marengereke,  K. Sornalakshmi,   "Automated Malicious Android App Detection using Machine Learning Methods", International Journal of Engineering Development and Research (IJEDR), ISSN:2321-9939, Volume.3, Issue 2, pp.191-197, May 2015, Available at :http://www.ijedr.org/papers/IJEDR1502035.pdf
Article Preview
|
|
||||||
|