Why GloVe Shows Negative Effects in Malware Classification

Abstract

The past decades witness the development of various Machine Learning (ML) models for malware classification. Semantic representation is a crucial basis for these classifiers. This paper aims to assess the effect of semantic representation methods on malware classifier performance. Two commonly-used semantic representation methods including N-gram and GloVe. We utilize diverse ML classifiers to conduct comparative experiments to analyze the capability of N-gram, GloVe and image-based methods for malware classification. We also analyze deeply the reason why the GloVe can produce negative effects on malware static analysis.