MalDeXA - A Malware Detection system using XGBoost on Amazon Web Services
Govind Thakur, Shreya Nayak, Ramchandra Sharad Mangrulkar · 2021 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES) · 2021
Machine learning, an upcoming field of Artificial Intelligence has developed rapidly since its emergence. Cybersecurity is one such pertinent domain which deals with Malware detection. Every malware has its distinctive means of creating destruction and also relies on the user's activity. Strains of malware could be dispatched over a link, mail, or any executable file. Corporations must be aware of the various susceptible attacks and devise security measures for the same. Gartner Research predicts that by 2022, the International Security Market will pass over the mark of $ 170 billion. However, a panacea for all viruses, attacks, and malware has not been developed yet. Research is required to understand both - the new types of malware and the various techniques used in their detection. This paper presents a systematic study of malware and compares various tree-based algorithms such as the Decision Tree, Adaboost Classifier, Random Forest Classifier, and XGBoost Classifier in their application as a malware detection system. It also provides both graphical and analytical analysis to help reach a worthwhile inference.