Static Analysis on Disassembled Files: A Deep Learning Approach to Malware Classification

Abstract

The cybernetic environment is hostile. An infinitude of gadgets with access to fast networks and the massive use of social networks considerably raised the number of vectors of malware propagation. Deep Learning models achieved great results in many different areas, including security-related tasks, such as static and dynamic malware analysis. This paper details a deep learning approach to the problem of malware classification using only the disassembled artifact's code as input. We show competitive performance when comparing to other solutions that use a higher degree of knowledge.