A dynamic malware detection in cloud platform

Abstract

Cloud computing not only provides high availability on elastic resources, scalable, and cost-efficient. The platform is also widely used in information technology (IT) to support technology infrastructure and services. However, due to the complex environment and scalability of services, one of the highest security issues is malware attacks, where some of the antivirus scanner unable to detect metamorphic malware or encrypted malware where these kinds of malware able to bypass some traditional protection solution. This is why a high recognition rate and good precision detection are important to eliminate a high false-positive rate. Machine Learning (ML) classifiers are a critical role in artificial intelligent-system. However, machine learning will require to learn from the high amplitude of input data; classify then only able to generate a reliable model with a high detection rate. The objective of this work is to study and performs detection based on dynamic malware analysis and classification is through the WEKA classifier and Random Forest Jupyter Notebook. There are three classifiers chosen in this work, which are Random Forest, J-48, and Naive Bayes with 10-folds validation from the WEKA tool and another additional classifier from Random Forest - Jupyter Notebook to substantiate the accuracy.