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{177645,
        author = {Dr.P.Ramya and Durga S and Perumal S and Prasanna V and Nethra V},
        title = {Cyber Sentry: A Machine Learning Framework for Proactive Detection and Prevention of Malicious URLs},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {12},
        pages = {1161-1167},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=177645},
        abstract = {The proliferation of malicious URLs poses a significant cybersecurity threat, serving as primary vectors for phishing attacks, malware distribution, and other cybercrimes. Traditional methods like blacklist filtering often struggle to keep pace with the dynamic and rapidly evolving nature of these threats. This paper introduces "Cyber Sentry," a machine learning-based framework designed for the effective detection and prevention of malicious URLs. Cyber Sentry leverages a hybrid feature set, combining lexical analysis of URL strings with selected host-based information, to train robust classification models. We evaluate the performance of several machine learning algorithms, including Support Vector Machines (SVM), Random Forest (RF), and Logistic Regression (LR), on a comprehensive dataset comprising benign and malicious URLs sourced from publicly available repositories like Phish Tank, Open Phish, and the Common Crawl corpus. Our experimental results demonstrate that the Random Forest classifier achieves superior performance, attaining an accuracy of 98.2% and an F1-score of 98.1%, significantly outperforming traditional blacklist approaches and demonstrating the viability of machine learning for proactive URL threat mitigation. The framework is designed for potential integration into various security systems, such as web proxies, browser extensions, or DNS filters.},
        keywords = {Malicious URL Detection, Machine Learning, Cybersecurity, Phishing Detection, Feature Engineering, Random Forest, Threat Prevention.},
        month = {May},
        }