A dynamic malware detection in cloud platform

Cloud Computing platform is the practices of remote manage network resources such as storage, application hosted on the internet rather than physical server or personal computer. Hence cloud computing not only provides high availability on elastic resources, scalable and cost efficient. This is why this this platform is widely used in information technology (IT) to support technology infrastructure and services. However, due to the complexity environment and scalability of services, one of a highest security issue is malware attacks; where some of the antivirus scanner unable to detect metamorphic malware or encrypted malware where these kind of malware able to bypass some traditional protection solution. This is why a high recognition rate and a good precision detection are important to eliminate high false positive rate. Machine learning (ML) classifiers are critical role in the artificial intelligent-system such as medical assistance detect whether the cell is cancerous or benign or to convert the spoken audio file into a text file. However machine learning will require learn from high amplitude of input data; classify then only able to generate a reliable model with high detection rate. The objective in this work is to study and performs detection based on dynamic malware analysis and classification is through WEKA classifier and Random Forest Jupyter Notebook. In this work we assess five classifiers, for instance the Random Forest in WEKA, Decision Tree (J48) in WEKA and Bayes Network (BN) in WEKA tool, and Random Forest in Jupyter Notebook comprised 9600 malware dataset obtained from Kaggle to exhibit the model’s effectiveness, out of which additional 600 are new malware dataset, whereby previous solution consist 9000 malware dataset.

Text FSKTM 2019 41 - IR.pdf Download (950kB)

Actions (login required)

View Item