Characterizing Evaluation Practices of Intrusion Detection Methods for Smartphones


The appearance of a new Android platform and its popularity has resulted in a sharp rise in the number of reported vulnerabilities and consequently in the number of mobile threats. Mobile malware, a dominant threat for modern mobile devices, was almost non-existent before the official release of the Android platform in 2008. The rapid development of mobile platform apps and app markets coupled with the open nature of the Android platform triggered an explosive growth of specialized malware and subsequent search for effective defence mechanisms. In spite of considerable research efforts in this area, the majority of the proposed solutions have seen limited success, which has been attributed in the research community to the lack of proper datasets, lack of validation and other deficiencies of the experiments. We feel that many of these shortcomings are due to immaturity of the field and a lack of established and organized practice. To remedy the problem, we investigated the employed experimentation practices adopted by the smartphone security community through a review of 120 studies published during the period between 2008 2013. In this paper, we give an overview of the research in the field of intrusion detection techniques for the Android platform and explore the deficiencies of the existing experimentation practices. Based on our analysis we present a set of guidelines that could help researchers to avoid common pitfalls and improve the quality of their work. River Journal, 1–36. c © 2014 River Publishers. All rights reserved. 2 A. Alzahrani et al.

11 Figures and Tables

Cite this paper

@inproceedings{Alzahrani2014CharacterizingEP, title={Characterizing Evaluation Practices of Intrusion Detection Methods for Smartphones}, author={Abdullah J. Alzahrani and Natalia Stakhanova and Hugo Gonzalez and Ali A. Ghorbani}, year={2014} }