Background & Objective: In this paper, malicious apps detection system is implemented
using machine learning algorithms. For this 330 permission based features of 558 android applications
are taken into consideration.
Methods: The main motto of this work is to develop a model which can effectively detect the malicious
and benign apps. In this we have used six feature selection techniques which will extract
important features from 330 permission based features of 558 apps and further fourteen classification
algorithms are applied using Python language.
Results: In this paper, an efficient model for detecting malicious apps has been proposed.
Conclusion: Proposed model is able to detect malicious apps approx. 3% better than existing system.