Malware Detection Using a Random Forest Method Trained on a Balanced Synthetic Dataset

The accuracy of malware detection is closely related to the available datasets, which are often small and imbalanced. To overcome these challenges, this study proposed a new method that creates synthetic malware data and increases the size and balance by generating several data sets with a flow-base...

Full description

Saved in:
Bibliographic Details
Main Authors: Neo Onica Matsobane, Sello Mokwena
Format: Article
Language:English
Published: IMS Vogosca 2025-03-01
Series:Science, Engineering and Technology
Subjects:
Online Access:https://setjournal.com/SET/article/view/167
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849735959054123008
author Neo Onica Matsobane
Sello Mokwena
author_facet Neo Onica Matsobane
Sello Mokwena
author_sort Neo Onica Matsobane
collection DOAJ
description The accuracy of malware detection is closely related to the available datasets, which are often small and imbalanced. To overcome these challenges, this study proposed a new method that creates synthetic malware data and increases the size and balance by generating several data sets with a flow-based model. Subsequently, a random forest classifier is fitted on this augmented dataset. This study aimed to analyze the generation of synthetic data based on flow-based models and the impact of synthetic data generation on the performance of a random forest for malware detection. A flow-based model was used to generate a balanced synthetic dataset based on the CICMalDroid2020 dataset. The generated data was used for feature selection and engineering to optimize the Random Forest model. The experimental results demonstrate the effectiveness of the proposed approach. The flow-based model generated an additional 13,402 samples, massively increasing the dataset size, even though the original dataset had only 11,598 data entries. After training on the synthetic augmented dataset, the Random Forest model achieved better performance compared to the original dataset evaluation with metrics precision (93%), recall (100%), balanced precision (96%), and the F1 score (91%). The results show that flow-based model-generated synthetic data can significantly enhance malware detection capabilities.
format Article
id doaj-art-56253d52cc6f47a7bd0345c579513dfe
institution DOAJ
issn 2831-1043
2744-2527
language English
publishDate 2025-03-01
publisher IMS Vogosca
record_format Article
series Science, Engineering and Technology
spelling doaj-art-56253d52cc6f47a7bd0345c579513dfe2025-08-20T03:07:24ZengIMS VogoscaScience, Engineering and Technology2831-10432744-25272025-03-015110.54327/set2025/v5.i1.167Malware Detection Using a Random Forest Method Trained on a Balanced Synthetic DatasetNeo Onica Matsobane0https://orcid.org/0000-0001-7912-7853Sello Mokwena1https://orcid.org/0000-0002-6160-863XDepartment of Computer Sciences, Faculty of Science and Agriculture, University of Limpopo, Polokwane, South Africa.Department of Computer Sciences, Faculty of Science and Agriculture, University of Limpopo, Polokwane, South Africa.The accuracy of malware detection is closely related to the available datasets, which are often small and imbalanced. To overcome these challenges, this study proposed a new method that creates synthetic malware data and increases the size and balance by generating several data sets with a flow-based model. Subsequently, a random forest classifier is fitted on this augmented dataset. This study aimed to analyze the generation of synthetic data based on flow-based models and the impact of synthetic data generation on the performance of a random forest for malware detection. A flow-based model was used to generate a balanced synthetic dataset based on the CICMalDroid2020 dataset. The generated data was used for feature selection and engineering to optimize the Random Forest model. The experimental results demonstrate the effectiveness of the proposed approach. The flow-based model generated an additional 13,402 samples, massively increasing the dataset size, even though the original dataset had only 11,598 data entries. After training on the synthetic augmented dataset, the Random Forest model achieved better performance compared to the original dataset evaluation with metrics precision (93%), recall (100%), balanced precision (96%), and the F1 score (91%). The results show that flow-based model-generated synthetic data can significantly enhance malware detection capabilities. https://setjournal.com/SET/article/view/167malware detectionaccuracyrandom forestflow-based modelbalanced datasetsynthetic dataset
spellingShingle Neo Onica Matsobane
Sello Mokwena
Malware Detection Using a Random Forest Method Trained on a Balanced Synthetic Dataset
Science, Engineering and Technology
malware detection
accuracy
random forest
flow-based model
balanced dataset
synthetic dataset
title Malware Detection Using a Random Forest Method Trained on a Balanced Synthetic Dataset
title_full Malware Detection Using a Random Forest Method Trained on a Balanced Synthetic Dataset
title_fullStr Malware Detection Using a Random Forest Method Trained on a Balanced Synthetic Dataset
title_full_unstemmed Malware Detection Using a Random Forest Method Trained on a Balanced Synthetic Dataset
title_short Malware Detection Using a Random Forest Method Trained on a Balanced Synthetic Dataset
title_sort malware detection using a random forest method trained on a balanced synthetic dataset
topic malware detection
accuracy
random forest
flow-based model
balanced dataset
synthetic dataset
url https://setjournal.com/SET/article/view/167
work_keys_str_mv AT neoonicamatsobane malwaredetectionusingarandomforestmethodtrainedonabalancedsyntheticdataset
AT sellomokwena malwaredetectionusingarandomforestmethodtrainedonabalancedsyntheticdataset