Please use this identifier to cite or link to this item: http://ir.juit.ac.in:8080/jspui/jspui/handle/123456789/7235
Title: Malicious Android Application Detection using Machine Learning
Authors: Kapoor, Aditya
Kushwaha, Himanshu
Gandotra, Ekta [Guided by]
Keywords: Malicious
Android application
Machine learning
Issue Date: 2019
Publisher: Jaypee University of Information Technology, Solan, H.P.
Abstract: Since the launch of the smartphones, their usage is increasing exponentially and it has become an important part of our lives. We are very much dependent on smartphones for our daily routine and use numerous applications both from the play store or the third party applications. Most of the times the applications downloaded from unofficial sources pose a threat as it doesn’t undergoes the necessary checks or mechanisms to validate the authenticity of these applications and maybe infected with malware. The malware infected applications can lead to leakage of user’s personal data or for getting restricted access to the system. Initially, the use of signatures, which are a small number of bytes from the virus, were carried out to check the viruses but its database needs to be updated regularly. In this project, we present an alternative of virus detection by using machine learning techniques we extracted the permissions and created a dataset and used machine learning algorithms for classifying the applications into malicious or benign and compared their results to determine the best algorithm suiting for our dataset. Furthermore, we have converted the Android application samples into images and explored how convolutional neural network works for the classification of application into malicious or benign.
URI: http://ir.juit.ac.in:8080/jspui/jspui/handle/123456789/7235
Appears in Collections:B.Tech. Project Reports

Files in This Item:
File Description SizeFormat 
Malicious Android Application Detection using Machine Learning.pdf4.95 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.