A static approach towards mobile botnet detection
- 1 August 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 9, 563-567
Abstract
The use of mobile devices, including smartphones, tablets, smart watches and notebooks are increasing day by day in our societies. They are usually connected to the Internet and offer nearly the same functionality, same memory and same speed like a PC. To get more benefits from these mobile devices, applications should be installed in advance. These applications are available from third party websites, such as google play store etc. In existing mobile devices operating systems, Android is very easy to attack because of its open source environment. Android OS use of open source facilty attracts malware developers to target mobile devices with their new malicious applications having botnet capabilities. Mobile botnet is one of the crucial threat to mobile devices. In this study we propose a static approach towards mobile botnet detection. This technique combines MD5, permissions, broadcast receivers as well as background services and uses machine learning algorithm to detect those applications that have capabilities for mobile botnets. In this technique, the given features are extracted from android applications in order to build a machine learning classifier for detection of mobile botnet attacks. Initial experiments conducted on a known and recently updated dataset: UNB ISCX Android botnet dataset, having the combination of 14 different malware families, shows the efficiency of our approach. The given research is in progress.Keywords
This publication has 10 references indexed in Scilit:
- Intrusion response systems: Foundations, design, and challengesJournal of Network and Computer Applications, 2016
- Android Botnets: What URLs are Telling Us2015
- Apposcopy: semantics-based detection of Android malware through static analysis2014
- Papilio: Visualizing Android Application PermissionsComputer Graphics Forum, 2014
- SMS mobile botnet detection using a multi-agent system2014
- Evolution, Detection and Analysis of Malware for Smart DevicesIEEE Communications Surveys & Tutorials, 2013
- Mobile Network Anomaly Detection and Mitigation: The NEMESYS Approach2013
- MAMA: MANIFEST ANALYSIS FOR MALWARE DETECTION IN ANDROIDCybernetics and Systems, 2013
- Android permissions2012
- Mobile Botnet Detection Using Network Forensics2010