A hybrid approach of mobile malware detection in Android

摘要: Android security incidents occurred frequently in recent years. This motivates us to study mobile app security, especially open operating system. In this paper, we propose a novel hybrid approach for malware detection by adopting both dynamic analysis and static analysis. We collect execution data of sample benign apps using net_link technology generate patterns system calls related file network access. Furthermore, build up malicious pattern set normal comparing the with each other. For detecting an unknown app, use method its calling data. then compare them sets offline order judge app. Based on test apps, found that our achieves better success rate than some methods either or What is more, proposed generic, which can detect different types effectively. Its accuracy be further improved since automatically optimized through self-learning. Hybrid based patterns.Implementation performance platform.Self-improvement automatic optimization sets.Detection generality showed comparison.