# An Empirical Analysis of Image-Based Learning Techniques for Malware Classification

arXiv: https://arxiv.org/abs/2103.13827 · HTML: https://mlsanity.com/paper/2103.13827/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 41 references that are in the map.
- First posted on arXiv 24 Mar 2021.

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

- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [Transfer Learning for Image-Based Malware Classification](https://mlsanity.com/paper/1903.11551/) (2019)

## Built on by (most cited first, 5 of 5)

- [Generative Adversarial Networks and Image-Based Malware Classification](https://mlsanity.com/paper/2207.00421/) (2022)
- [A Natural Language Processing Approach to Malware Classification](https://mlsanity.com/paper/2307.11032/) (2023)
- [Auxiliary-Classifier GAN for Malware Analysis](https://mlsanity.com/paper/2107.01620/) (2021)
- [A Comparison of Selected Image Transformation Techniques for Malware Classification](https://mlsanity.com/paper/2509.10838/) (2025)
- [BinImg2Vec: Augmenting Malware Binary Image Classification with Data2Vec](https://mlsanity.com/paper/2209.00782/) (2022)

## Abstract (arXiv)

In this paper, we consider malware classification using deep learning techniques and image-based features. We employ a wide variety of deep learning techniques, including multilayer perceptrons (MLP), convolutional neural networks (CNN), long short-term memory (LSTM), and gated recurrent units (GRU). Amongst our CNN experiments, transfer learning plays a prominent role specifically, we test the VGG-19 and ResNet152 models. As compared to previous work, the results presented in this paper are based on a larger and more diverse malware dataset, we consider a wider array of features, and we experiment with a much greater variety of learning techniques. Consequently, our results are the most comprehensive and complete that have yet been published.