Real-Time Ransomware Detection Using Optimized XGBoost: A Behavior-Based Approach for Cybersecurity Defense

Rejoice Angelina Muppidi, C. Sureshkumar

2025

Abstract

Ransomware is one of the greatest cybersecurity and information security challenges, having significant impacts financially and operationally for numerous industries. Detection processes continue to rely on pre-defined approaches which are usually incorrect and take too long to reveal new types of ransomware. This work proposes a Ransomware Attack Detection Tool with Integrated Machine Learning (ML) for improving real time ransomware detection. We focus on literature review on existing solutions and research gaps regarding real time detection, efficiency, and classification accuracy. Our approach utilizes optimized feature selection, high-performance classification using XG Boost, and threat detection via Flask for real-time integration. The experiments conducted show enhanced accuracy and lessened false positives in contrast to the other methods. The framework proposed is effective at helping defend against ransomware attacks and improves overall cybersecurity posture.

Paper Citation

in Harvard Style

Muppidi R. and Sureshkumar C. (2025). Real-Time Ransomware Detection Using Optimized XGBoost: A Behavior-Based Approach for Cybersecurity Defense. In Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25; ISBN 978-989-758-777-1, SciTePress, pages 466-471. DOI: 10.5220/0013884900004919

in Bibtex Style

@conference{icrdicct`2525,
author={Rejoice Muppidi and C. Sureshkumar},
title={Real-Time Ransomware Detection Using Optimized XGBoost: A Behavior-Based Approach for Cybersecurity Defense},
booktitle={Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25},
year={2025},
pages={466-471},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013884900004919},
isbn={978-989-758-777-1},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 1st International Conference on Research and Development in Information, Communication, and Computing Technologies - ICRDICCT`25
TI - Real-Time Ransomware Detection Using Optimized XGBoost: A Behavior-Based Approach for Cybersecurity Defense
SN - 978-989-758-777-1
AU - Muppidi R.
AU - Sureshkumar C.
PY - 2025
SP - 466
EP - 471
DO - 10.5220/0013884900004919
PB - SciTePress