Towards an understanding of the impact of advertising on data leaks
International Journal of Security and Networks
Detecting malicious behaviour using supervised learning algorithms of the function calls
International Journal of Electronic Security and Digital Forensics
DroidLegacy: Automated Familial Classification of Android Malware
Proceedings of ACM SIGPLAN on Program Protection and Reverse Engineering Workshop 2014
| Hi-index | 0.00 |
Since its establishment, the Android applications market has been infected by a proliferation of malicious applications. Recent studies show that rogue developers are injecting malware into legitimate market applications which are then installed on open source sites for consumer uptake. Often, applications are infected several times. In this paper, we investigate the behavior of malicious Android applications, we present a simple and effective way to safely execute and analyze them. As part of this analysis, we use the Android application sandbox Droidbox to generate behavioral graphs for each sample and these provide the basis of the development of patterns to aid in identifying it. As a result, we are able to determine if family names have been correctly assigned by current anti-virus vendors. Our results indicate that the traditional anti-virus mechanisms are not able to correctly identify malicious Android applications.