--- Leveraging Behavioral Analysis and Machine Learning for Effective Ransomware Mitigation
Author(s): DAMIAN, Dorina-Mariana
Author(s) keywords: anomaly detection techniques, behavioral analysis, critical data, Machine Learning, ransomware
Reference keywords: anomaly detection, machine learning, ransomware
Abstract:
Ransomware attacks pose significant threats to individuals and organizations, causing data loss, financial damage, and operational disruptions. Traditional antivirus solutions often fail to detect new ransomware variants. This article proposes a proactive approach to ransomware mitigation by integrating behavioral analysis and machine learning algorithms into software solutions. By analyzing the behavior of files and processes, our solution aims to detect and prevent ransomware attacks before they can cause significant harm, thus protecting critical data and systems. By continuously monitoring process behaviors and employing anomaly detection techniques, this approach dynamically identifies and terminates malicious processes without relying on predefined signatures or process names. This paper details the implementation, working principles, and effectiveness of this solution through comprehensive analysis.
References:
[1]. R. Naydenov, S. Garcia, A. Gomaa, V. Valeros, A. Malatras, E. Tsekmezoglou, “ENISA threat landscape for ransomware attacks”, ENISA, 2022.
[2]. M. Aggarwal, “Ransomware Attack: An Evolving Targeted Threat”, 2023.
[3]. B.T. Magar, “Cactus Ransomware: How it works and how to respond? Emerging Threats Protection Report,” Emerging Threats Protection Report, Available: https://www.logpoint.com/wp-content/uploads/2023/12/et-cactus-4-12.pdf.
[4]. F.T. Liu, K.M. Ting, Z.-H. Zhou, “Isolation Forest”, IEEE International Conference on Data Mining, 2009.
[5]. S. Hariri, M. Carrasco, R. J. Brunner, “Extended Isolation Forest”, IEEE Transactions on Knowledge and Data Engineering, vol. 33, no. 4, April 2021.
[6]. D. Mohamed, A. El-Kilany, H. M. O. Mokhtar, “A Hybrid Model for Documents Representation,” International Journal of Advanced Computer Science and Applications, vol. 12, no. 3, pp. 317-324, 2021.
Article Title: Leveraging Behavioral Analysis and Machine Learning for Effective Ransomware Mitigation
Author(s): DAMIAN, Dorina-Mariana
Date of Publication: 2025-12-24
Publication: International Journal of Information Security and Cybercrime
ISSN: 2285-9225 e-ISSN: 2286-0096
Digital Object Identifier: 10.19107/IJISC.2025.02.04
Issue: Volume XIV, Issue 2, Year 2025
Section: Studies and Analysis of Cybercrime Phenomenon
Page Range: 39-44 (6 pages)
Copyright ©2012-2026
The International Journal of Information Security and Cybercrime (IJISC)
All rights reserved
The International Journal of Information Security and Cybercrime is a trademark of the Romanian Association for Information Security Assurance (RAISA).
No part of this publication may be reproduced, stored in a retrieval system, photocopied, recorded or archived, without the written permission from RAISA. When authors submit their papers for publication, they agree that the copyright for their article be transferred to the Romanian Association for Information Security Assurance, if the articles are accepted for publication. The copyright covers the exclusive rights to reproduce and distribute the article, including reprints and translations.