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{197044,
        author = {Ravu leela sudeep and Tammineni bhargav sai},
        title = {Hybrid Approach in Ransomware Recognition and Classification using Machine Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {9072-9080},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=197044},
        abstract = {Ransomware is currently a major threat to the digital infrastructure by encrypting sensitive data and demanding ransom payments for decrypting keys. Traditional detection approaches tend to be in catching up with the body of ransomware evolution and the increase of its sophistication. This project introduces the concept of a hybrid machine learning-based ransomware detection and classification system to analyse Portable Executable (PE) files. The method is to extract some important static features such as the entropy, version metadata, section characteristics of PE files to differentiate between legitimate programs and ransomware. The labeled dataset which consists of benign and malicious samples goes through preprocessing and feature selection procedure using an Extra Trees Classifier in order to select the most important attributes. A Random Forest Classifier, which was further fine-tuned using hyperparameter optimization, is trained on the selected features to help improve the accuracy of detection, by reducing false positives and false negatives. The system comes with a web-based, easy-to-use interface using Flask, allowing easy upload of new files and obtaining classification results in real-time. This hybrid approach helps with accuracy, adaptability, computational efficiency to be an effective solution to early ransomware recognition and mitigation},
        keywords = {Ransomware detection, Machine learning, Hybrid model, Portable Executable (PE) files, Feature extraction, Extra Trees Classifier, Random Forest Classifier, Entropy analysis, Cybersecurity, Flask interface.},
        month = {April},
        }