The usage of mobile devices is increasing exponentially. There were lots of critical applications such as banking to health applications are available on mobile devices through mobile applications. This penetration and spread of mobile applications brings some threats. Malicious software(Malware) is one of these dangers. Malware has the potential to cause damage to various scales such as theft of sensitive data, identity and credit card. To reduce the effects of these threats, antiviruses have been developed and malware analysis teams have been established, but human effort may be insufficient in the rapidly growing malware market. For this reason, automated malware scanning solutions should be developed by making use of machine learning algorithms. In this study, machine learning models were created by using the n-gram features of the smali files, which are the decompiled Android packages. The trained models are combined with different feature extraction and feature selection methods and as a result their performances are reported.
Software And Hardware
• Hardware: Processor: i3 ,i5 RAM: 4GB Hard disk: 16 GB • Software: operating System : Windws2000/XP/7/8/10 Anaconda,jupyter,spyder,flask Frontend :-python Backend:- MYSQL