Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{189559,
        author = {Aishwarya U and Faiz Aman and Archana K R and Keerthana A S and Spoorthy S G},
        title = {Ransomware Threat Detection and Mitigation Using Machine Learning Models},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {7},
        pages = {7095-7099},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=189559},
        abstract = {Ransomware attacks are leading to massive financial losses and interruptions in operations across the world. Conventional signature models are useless against new strains and zero-day attacks. In this paper, we have discussed the development of an intelligent machine learning model capable of real-time ransomware attack identification and mitigation. Our model uses an ensemble model consisting of 40% of the random forests model, 40% of the XG Boost model, and 20% of the neural network model for identifying behavioral patterns in PDF, docx, and JSON files. In our experimental results on the CIC-Evasive-PDFMal2022 dataset, we achieved an accuracy of 99.10%, precision of 98.72%, and a recall of 99.48%. We have wrapped our machine learning model in a Gradio framework for real-time identification and recommendation of the ransomware attack mitigation process in personal as well as professional settings.},
        keywords = {Adversarial Machine Learning, Cybersecurity, Ensemble Learning, Explainable AI, Malware Detection, Ransomware Threat Detection, Real-time Detection Systems, XGBoost},
        month = {December},
        }