# Transfer Learning for Image-Based Malware Classification

arXiv: https://arxiv.org/abs/1903.11551 · HTML: https://mlsanity.com/paper/1903.11551/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Jan 2019.

## Built on by (most cited first, 12 of 12)

- [A Survey of Malware Detection Using Deep Learning](https://mlsanity.com/paper/2407.19153/) (2024)
- [An Empirical Analysis of Image-Based Learning Techniques for Malware Classification](https://mlsanity.com/paper/2103.13827/) (2021)
- [A Natural Language Processing Approach to Malware Classification](https://mlsanity.com/paper/2307.11032/) (2023)
- [A Comprehensive Study on Learning-Based PE Malware Family Classification Methods](https://mlsanity.com/paper/2110.15552/) (2021)
- [New Approach to Malware Detection Using Optimized Convolutional Neural Network](https://mlsanity.com/paper/2301.11161/) (2023)
- [A Comparison of Selected Image Transformation Techniques for Malware Classification](https://mlsanity.com/paper/2509.10838/) (2025)
- [Improving Botnet Detection with Recurrent Neural Network and Transfer Learning](https://mlsanity.com/paper/2104.12602/) (2021)
- [MalGrid: Visualization Of Binary Features In Large Malware Corpora](https://mlsanity.com/paper/2211.02696/) (2022)
- [Malware Classification using a Hybrid Hidden Markov Model-Convolutional Neural Network](https://mlsanity.com/paper/2412.18932/) (2024)
- [ViPER: Vision-based Packing-Aware Encoder for Robust Malware Detection](https://mlsanity.com/paper/2606.12949/) (2026)
- [ThreatVisionAI: A Hybrid CNN-ViT Framework for Image-Based Malware Classification](https://mlsanity.com/paper/2607.03653/) (2026)
- [CAM-Guided Saliency Cutout and Image-Based Malware Classification](https://mlsanity.com/paper/2608.11634/) (2026)

## Abstract (arXiv)

In this paper, we consider the problem of malware detection and classification based on image analysis. We convert executable files to images and apply image recognition using deep learning (DL) models. To train these models, we employ transfer learning based on existing DL models that have been pre-trained on massive image datasets. We carry out various experiments with this technique and compare its performance to that of an extremely simple machine learning technique, namely, k-nearest neighbors (kNN). For our k-NN experiments, we use features extracted directly from executables, rather than image analysis. While our image-based DL technique performs well in the experiments, surprisingly, it is outperformed by k-NN. We show that DL models are better able to generalize the data, in the sense that they outperform k-NN in simulated zero-day experiments.