PIndroid: A novel Android malware detection system using ensemble learning methods

Idrees, F., Rajarajan, M., Conti, M., Chen, T. & Rahulamathavan, Y. (2017). PIndroid: A novel Android malware detection system using ensemble learning methods. Computers and Security, 68, pp. 36-46. doi: 10.1016/j.cose.2017.03.011

[img] Text - Accepted Version
Restricted to Repository staff only until 31 March 2018.
Available under License Creative Commons Attribution Non-commercial No Derivatives.

Download (625kB) | Request a copy

Abstract

The extensive use of smartphones has been a major driving force behind a drastic increase of malware attacks. Covert techniques used by the malware make them hard to detect with signature based methods. In this paper, we present PIndroid – a novel Permissions and Intents based framework for identifying Android malware apps. To the best of our knowledge, PIndroid is the first solution that uses a combination of permissions and intents supplemented with Ensemble methods for accurate malware detection. The proposed approach, when applied to 1,745 real world applications, provides 99.8% accuracy (which is best reported to date). Empirical results suggest that the proposed framework is effective in detection of malware apps.

Item Type: Article
Uncontrolled Keywords: Malware classification; Permissions; Intents; Ensemble methods; Colluding applications
Subjects: Q Science > QA Mathematics > QA76 Computer software
Divisions: School of Engineering & Mathematical Sciences > Engineering
URI: http://openaccess.city.ac.uk/id/eprint/17316

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics