Transfer Learning for Image-based Malware Classification

Niket Bhodia, Pratikkumar Prajapati, Fabio Di Troia, Mark Stamp

2019

Abstract

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 (k-NN). 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.

Paper Citation

in Harvard Style

Bhodia N., Prajapati P., Di Troia F. and Stamp M. (2019). Transfer Learning for Image-based Malware Classification.In Proceedings of the 5th International Conference on Information Systems Security and Privacy - Volume 1: ForSE, ISBN 978-989-758-359-9, pages 719-726. DOI: 10.5220/0007701407190726

in Bibtex Style

@conference{forse19,
author={Niket Bhodia and Pratikkumar Prajapati and Fabio Di Troia and Mark Stamp},
title={Transfer Learning for Image-based Malware Classification},
booktitle={Proceedings of the 5th International Conference on Information Systems Security and Privacy - Volume 1: ForSE,},
year={2019},
pages={719-726},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007701407190726},
isbn={978-989-758-359-9},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 5th International Conference on Information Systems Security and Privacy - Volume 1: ForSE,
TI - Transfer Learning for Image-based Malware Classification
SN - 978-989-758-359-9
AU - Bhodia N.
AU - Prajapati P.
AU - Di Troia F.
AU - Stamp M.
PY - 2019
SP - 719
EP - 726
DO - 10.5220/0007701407190726