MLRan: A Behavioural Dataset for Ransomware Analysis and Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Onwuegbuche, Faithful Chiagoziem, Olaoluwa, Adelodun, Jurcut, Anca Delia, Pasquale, Liliana
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909622077489152
author Onwuegbuche, Faithful Chiagoziem
Olaoluwa, Adelodun
Jurcut, Anca Delia
Pasquale, Liliana
author_facet Onwuegbuche, Faithful Chiagoziem
Olaoluwa, Adelodun
Jurcut, Anca Delia
Pasquale, Liliana
contents Ransomware remains a critical threat to cybersecurity, yet publicly available datasets for training machine learning-based ransomware detection models are scarce and often have limited sample size, diversity, and reproducibility. In this paper, we introduce MLRan, a behavioural ransomware dataset, comprising over 4,800 samples across 64 ransomware families and a balanced set of goodware samples. The samples span from 2006 to 2024 and encompass the four major types of ransomware: locker, crypto, ransomware-as-a-service, and modern variants. We also propose guidelines (GUIDE-MLRan), inspired by previous work, for constructing high-quality behavioural ransomware datasets, which informed the curation of our dataset. We evaluated the ransomware detection performance of several machine learning (ML) models using MLRan. For this purpose, we performed feature selection by conducting mutual information filtering to reduce the initial 6.4 million features to 24,162, followed by recursive feature elimination, yielding 483 highly informative features. The ML models achieved an accuracy, precision and recall of up to 98.7%, 98.9%, 98.5%, respectively. Using SHAP and LIME, we identified critical indicators of malicious behaviour, including registry tampering, strings, and API misuse. The dataset and source code for feature extraction, selection, ML training, and evaluation are available publicly to support replicability and encourage future research, which can be found at https://github.com/faithfulco/mlran.
format Preprint
id arxiv_https___arxiv_org_abs_2505_18613
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MLRan: A Behavioural Dataset for Ransomware Analysis and Detection
Onwuegbuche, Faithful Chiagoziem
Olaoluwa, Adelodun
Jurcut, Anca Delia
Pasquale, Liliana
Cryptography and Security
Machine Learning
Ransomware remains a critical threat to cybersecurity, yet publicly available datasets for training machine learning-based ransomware detection models are scarce and often have limited sample size, diversity, and reproducibility. In this paper, we introduce MLRan, a behavioural ransomware dataset, comprising over 4,800 samples across 64 ransomware families and a balanced set of goodware samples. The samples span from 2006 to 2024 and encompass the four major types of ransomware: locker, crypto, ransomware-as-a-service, and modern variants. We also propose guidelines (GUIDE-MLRan), inspired by previous work, for constructing high-quality behavioural ransomware datasets, which informed the curation of our dataset. We evaluated the ransomware detection performance of several machine learning (ML) models using MLRan. For this purpose, we performed feature selection by conducting mutual information filtering to reduce the initial 6.4 million features to 24,162, followed by recursive feature elimination, yielding 483 highly informative features. The ML models achieved an accuracy, precision and recall of up to 98.7%, 98.9%, 98.5%, respectively. Using SHAP and LIME, we identified critical indicators of malicious behaviour, including registry tampering, strings, and API misuse. The dataset and source code for feature extraction, selection, ML training, and evaluation are available publicly to support replicability and encourage future research, which can be found at https://github.com/faithfulco/mlran.
title MLRan: A Behavioural Dataset for Ransomware Analysis and Detection
topic Cryptography and Security
Machine Learning
url https://arxiv.org/abs/2505.18613