# A Novel Feature Representation for Malware Classification

arXiv: https://arxiv.org/abs/2210.09580 · HTML: https://mlsanity.com/paper/2210.09580/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 44 references that are in the map.
- First posted on arXiv 18 Oct 2022.

## Builds on (most cited first, 3 of 3)

- [Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks](https://mlsanity.com/paper/1909.03496/) (2019)
- [Learning Semantic Program Embeddings with Graph Interval Neural Network](https://mlsanity.com/paper/2005.09997/) (2020)
- [Empirical Network Structure of Malicious Programs](https://mlsanity.com/paper/2210.08034/) (2022)

## Built on by (most cited first, 1 of 1)

- [kNN Classification of Malware Data Dependency Graph Features](https://mlsanity.com/paper/2406.02654/) (2024)

## Abstract (arXiv)

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.