A Non-Intrusive Machine Learning Solution to Malware Detection and Data Theft Classification in Smartphones

This repository contains the code for the paper titled "A Non-Intrusive Machine Learning Solution for Malware Detection and Data Theft Classification in Smartphones" which has been accepted at the International Conference on Computational Science (ICCS) 2021, Kraków, Poland.

The paper proposes a non-intrusive machine learning solution to not only detect malware intrusion but also identify the type of data stolen for any app under supervision in an Android device. We do this with android usage data obtained by utilizing a publicly available data collection framework-- SherLock. We test the performance of our architecture for multiple users on real-world data collected using the same framework. Our method exhibits less than 9% inaccuracy in detecting malware and can classify with 83% certainty on the type of data that is being stolen.

Each folder details a section of our solution:

1. Merge

2. Feature Selection

3. Models

4. Visuals

Authors : Sai Vishwanath Venkatesh, Prasanna Kumaran D, Joish J Bosco, Pravin Kumaar R  and Vineeth Vijayaraghavan