EMULATOR vs REAL PHONE: Android Malware Detection Using Machine Learning

摘要: The Android operating system has become the most popular for smartphones and tablets leading to a rapid rise in malware. Sophisticated malware employ detection avoidance techniques order hide their malicious activities from analysis tools. These include wide range of anti-emulator techniques, where programs attempt by detecting emulator. For this reason, countermeasures against anti-emulation are becoming increasingly important detection. Analysis based on real devices can alleviate problems as well improve effectiveness dynamic analysis. Hence, paper we present an investigation machine learning using devices. A tool is implemented automatically extract features phones through several experiments, comparative emulator vs. device means algorithms undertaken. Our study shows that could be extracted more effectively on-device compared emulators. It was also found approximately 24% apps were successfully analysed phone. Furthermore, all studied performed better when applied