English

A Novel Feature Representation for Malware Classification

Cryptography and Security 2022-10-19 v1 Machine Learning

Abstract

In this study we have presented a novel feature representation for malicious programs that can be used for malware classification. We have shown how to construct the features in a bottom-up approach, and analyzed the overlap of malicious and benign programs in terms of their components. We have shown that our method of analysis offers an increase in feature resolution that is descriptive of data movement in comparison to tf-idf features.

Keywords

Cite

@article{arxiv.2210.09580,
  title  = {A Novel Feature Representation for Malware Classification},
  author = {John Musgrave and Temesguen Messay-Kebede and David Kapp and Anca Ralescu},
  journal= {arXiv preprint arXiv:2210.09580},
  year   = {2022}
}

Comments

arXiv admin note: text overlap with arXiv:2210.08034

R2 v1 2026-06-28T03:53:05.499Z