| Popis: |
With the openness and growing popularity of Android Operating system all over the world, it has become a target of attack for Malware authors who are determined to take advantage of over 2.5 billion monthly active users of Android devices. Despite Google’s various protection measures, android malware continues to grow in complexity and scope. In recent time, many research efforts have focused on detecting malware on the Android operating system using both static and dynamic approaches. Most of the existing techniques are still not perfect because of the problems of false positive, false negative and high detection time. In this work, a Priority Execution-based Approach for Detecting Android Malware (PEDAM) is proposed to solve some of these problems. In PEDAM, a two-phase dynamic analysis scheme is used for malware analysis. The first phase involves the use of a time-based filter for prioritizing the android application that will execute based on permissions and intents. Any suspected samples not captured in the first phase are further analysed in the second phase, which does behavioural analysis using Support Vector Machine classifier to analyse permissions, intent filters and Activity features set for effective detection. The evaluation of the proposed model on different Android malware families’ shows that PEDAM outperformed another android-based malware detection system known as Iterative Classifier Fusion System (ICFS) with improved accuracy of 1.04%. These results indicated that the approach could be deployed for detection of android malware. |
