#Android mobile security by detecting and classification of malware based on permissions using machine learning algorithms. Viruses was taken from VirusSign | Malware Research & Data Center(2018),and Benign apps are downloaded form Google Play Store Trending apps of 2018.
Android occupies a major share in the mobile application market. Android mobiles have become an easy target for the attackers. The main reason is the user ignorance in the process of installing and usage of the apps. Android malware can be detected based on the permissions it requests from the user. Several machine learning algorithms are being used in the detection of android malware based on the list of permissions enabled for each app. Research Paper: 1.http://ieeexplore.ieee.org/document/8058358/?reload=true 2.http://ieeexplore.ieee.org/abstract/document/8117152/ We have get the idea from the Research paper's,and now working to make it a complete product,For that we have created a Website and Mobile App. We have downloaded 1000 Viruses and 1000 sample apps for making the data-set. In the Training Using Random forest we got the 98% accuracy and then in the testing phase of 500(250 viruses,250 sample apps ),we got 90% accuracy.
Website: Submit Apk file,we will decompile the apk and extract the permission and send to the API. Mobile App; Collect all the permissions of installed applications and send it to the API. API: using c# we have created the data model which predict the about the apps,that they are virus or not .