A Hybrid Ensemble Learning Framework for Efficient and Real-Time Phishing Website Detection Using Optimized URL and Domain Features
Dandao Xuebao/Journal of Ballistics · 10.06.2026 · 38 (2) · 362-371
DOI: 10.52783/dxjb.v38.351 ↗Kurz gefasst
Fachartikel in der Zeitschrift Dandao Xuebao/Journal of Ballistics, online erschienen am 10.06.2026. Verfasst von Anjali Sharma und 1 weiteren Autor:innen.
Abstract (Originalsprache)
Phishing attacks continue to pose a significant threat to cybersecurity by exploiting deceptive URLs and malicious domains. This paper proposes a hybrid ensemble learning framework for accurate and real-time phishing detection using only URL and domain-based features. Unlike traditional approaches, the proposed model integrates Random Forest and XGBoost within an optimized ensemble architecture, enhanced by feature selection techniques to reduce dimensionality and improve computational efficiency. Two benchmark datasets, PhiUSIIL and LegitPhish, are utilized to validate the robustness of the system. Extensive experiments demonstrate that the proposed hybrid model achieves superior performance with an accuracy of 97.2% and ROC-AUC of 0.99, outperforming conventional machine learning classifiers. The proposed framework is lightweight, privacy-preserving, and suitable for real-time deployment in browser extensions and email filtering systems.
Zitieren
APA
Sharma, A., & Rajput, A. (2026). A Hybrid Ensemble Learning Framework for Efficient and Real-Time Phishing Website Detection Using Optimized URL and Domain Features. Dandao Xuebao/Journal of Ballistics, 38(2), 362-371. https://doi.org/10.52783/dxjb.v38.351
Vancouver
Sharma A, Rajput A. A Hybrid Ensemble Learning Framework for Efficient and Real-Time Phishing Website Detection Using Optimized URL and Domain Features. Dandao Xuebao/Journal of Ballistics. 2026;38(2):362-371. doi:10.52783/dxjb.v38.351
BibTeX
@article{Sharma2026,
author = {Sharma, Anjali and Rajput, Ayan},
title = {A Hybrid Ensemble Learning Framework for Efficient and Real-Time Phishing Website Detection Using Optimized URL and Domain Features},
journal = {Dandao Xuebao/Journal of Ballistics},
year = {2026},
volume = {38},
number = {2},
pages = {362--371},
doi = {10.52783/dxjb.v38.351}
}
EUVIMED