Malware Detection Using Machine Learning

Authors: Asim Azhar, Richa Gupta, Mudita Saxena, Dipanshu Singh, Rahul Anjana

Abstract: This project focuses on detecting Malicious Android applications using supervised machine learning techniques. A permission based dataset is used where each application is represented by behavioral features such as requested permission. After preprocessing the dataset, machine learning algorithms including Random Forest, Decision tree and Naive Bayes are implemented using the WEKA framework in Java. The models are evaluated using 10-fold cross validation and standard performance metrics. The objective of the project is to develop an automated, accurate and safe malware detection system without executing malicious code.

DOI: https://doi.org/10.5281/zenodo.19639505