Multifamily malware models
Publication Date
3-1-2020
Document Type
Article
Publication Title
Journal of Computer Virology and Hacking Techniques
Volume
16
Issue
1
DOI
10.1007/s11416-019-00345-8
First Page
79
Last Page
92
Abstract
When training a machine learning model, there is likely to be a tradeoff between accuracy and the diversity of the dataset. Previous research has shown that if we train a model to detect one specific malware family, we generally obtain stronger results as compared to a case where we train a single model on multiple diverse families. However, during the detection phase, it would be more efficient to have a single model that can reliably detect multiple families, rather than having to score each sample against multiple models. In this research, we conduct experiments based on byte n-gram features to quantify the relationship between the generality of the training dataset and the accuracy of the corresponding machine learning models, all within the context of the malware detection problem. We find that neighborhood-based algorithms generalize surprisingly well, far outperforming the other machine learning techniques considered.
Department
Computer Science
Recommended Citation
Samanvitha Basole, Fabio Di Troia, and Mark Stamp. "Multifamily malware models" Journal of Computer Virology and Hacking Techniques (2020): 79-92. https://doi.org/10.1007/s11416-019-00345-8
