Malware Detection Using Machine Learning Classifiers

Abstract

With the growth of technology, and the exponential amount of data that is being generated, the main challenge is to figure out how to protect this data from unauthorized access. Over the last couple of years, researchers have struggled to come up with a best solution that would handle this problem. The signature-based detection was the standard method used to detect malware. Regrettably, traditional technologies are no longer capable of providing adequate protection. In this work, we proposed a protection system where we trained different models in machine learning to learn from malicious and benign files to allow future prediction. We trained three classifiers in this work, Random Forest, Decision Tree, and KNearest Neighbors on the data. Random Forest gives the best result with an FPR value of 0.0208 and an accuracy of 98%.