DENDROID: A text mining approach to analyzing and classifying code structures in Android malware families Articles uri icon

publication date

  • March 2014

start page

  • 1104

end page

  • 1117

issue

  • 4

volume

  • 41

international standard serial number (ISSN)

  • 0957-4174

electronic international standard serial number (EISSN)

  • 1873-6793

abstract

  • The rapid proliferation of smartphones over the last few years has come hand in hand with and impressive growth in the number and sophistication of malicious apps targetting smartphone users. The availability of reuse-oriented development methodologies and automated malware production tools makes exceedingly easy to produce new specimens. As a result, market operators and malware analysts are increasingly overwhelmed by the amount of newly discovered samples that must be analyzed. This situation has stimulated research in intelligent instruments to automate parts of the malware analysis process. In this paper, we introduce DENDROID, a system based on text mining and information retrieval techniques for this task. Our approach is motivated by a statistical analysis of the code structures found in a dataset of ANDROID OS malware families, which reveals some parallelisms with classical problems in those domains. We then adapt the standard Vector Space Model and reformulate the modelling process followed in text mining applications. This enables us to measure similarity between malware samples, which is then used to automatically classify them into families. We also investigate the application of hierarchical clustering over the feature vectors obtained for each malware family. The resulting dendo-grams resemble the so-called phylogenetic trees for biological species, allowing us to conjecture about evolutionary relationships among families. Our experimental results suggest that the approach is remarkably accurate and deals efficiently with large databases of malware instances. (C) 2013 Elsevier Ltd. All rights reserved.

keywords

  • malware analysis ; software similarity and classification; text mining; information retrieval; smartphones; android os