A Novel Neural Network-Based Malware Severity Classification System

Malware has been an increasing threat to computer users. Different pieces of malware have different damage potential depending on their objectives and functionalities. In the literature, there are many studies that focus on automatically identifying malware with their families. However, there is a lack of focus on automatically identifying the severity level of malware samples. In this paper, we propose a dedicated neural network-based malware severity classification method. It is developed based on the clustering analysis of malware functions. Experimental results show that the proposed method outperforms previously proposed machine learning methods for malware classification on the severity classification problem.