Malware Classification with Word Embedding Features

TL;DR

This paper introduces a hybrid malware classification approach using Word2Vec and HMM2Vec embeddings derived from opcode sequences, combined with various classifiers, demonstrating superior experimental results across malware families.

Contribution

It presents a novel feature engineering method combining HMM2Vec and Word2Vec embeddings for malware classification, extending previous work significantly.

Findings

Effective malware classification with improved accuracy

Successful application of hybrid embedding features

Extensive experiments across multiple malware families

Abstract

Malware classification is an important and challenging problem in information security. Modern malware classification techniques rely on machine learning models that can be trained on features such as opcode sequences, API calls, and byte $n$-grams, among many others. In this research, we consider opcode features. We implement hybrid machine learning techniques, where we engineer feature vectors by training hidden Markov models -- a technique that we refer to as HMM2Vec -- and Word2Vec embeddings on these opcode sequences. The resulting HMM2Vec and Word2Vec embedding vectors are then used as features for classification algorithms. Specifically, we consider support vector machine (SVM), $k$-nearest neighbor ($k$-NN), random forest (RF), and convolutional neural network (CNN) classifiers. We conduct substantial experiments over a variety of malware families. Our experiments extend well beyond any previous work in this field.