Phishing Website Detection Using Ensemble Machine Learning Techniques

DOI

10.2991/978-94-6463-858-5_53How to use a DOI?

Keywords

Xgb- Extreme Gradient Boosting; Uniform Resource Locator(URL); Natural Language Processing (NLP); Hyper Text Marked Language (HTML); Deep Learning

Abstract

Phishing attacks exploit users’ trust to steal sensitive information through fraudulent websites that mimic legitimate platforms, leading to identity theft, financial fraud, and unautho- rized data access. Traditional detection methods, such as black- lists and heuristic-based approaches, struggle against rapidly evolving phishing tactics due to their reliance on predefined patterns. Machine learning-based techniques provide a dynamic solution by analyzing website attributes such as URL structure, domain characteristics, and webpage content. In this study, we propose an ensemble learning-based phishing detection system that integrates multiple classifiers, including Random Forest, XGBoost, and Support Vector Machines (SVM), to enhance detection performance. Key phishing indicators such as domain age, URL length, special character presence, SSL certificate validity, and suspicious HTML elements are extracted and pro- cessed through an ensemble of classifiers, reducing false positives and enhancing detection robustness against adversarial phishing tactics. The system is trained on a diverse dataset comprising legitimate and phishing websites, ensuring generalizability across different phishing strategies. Experimental results demonstrate that our ensemble model outperforms traditional methods in accuracy and reliability, effectively detecting phishing attempts with minimal false positives and negatives. Additionally, the model’s computational efficiency ensures its practical deployment in various security environments. Comparative analysis with existing methods highlights the superiority of our approach in terms of detection rate and adaptability. The model is further strengthened through adaptive learning mechanisms, allowing continuous updates with newly detected phishing instances, while integrating security measures such as user feedback loops and active threat monitoring further enhances its phishing detection capabilities.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - V. Krishna Sameera
AU  - D. Kiran
AU  - N. Mohana Likitha
AU  - CH. Naveen
AU  - Md. Gulkhan
PY  - 2025
DA  - 2025/11/04
TI  - Phishing Website Detection Using Ensemble Machine Learning Techniques
BT  - Proceedings of International Conference on Computer Science and Communication Engineering (ICCSCE 2025)
PB  - Atlantis Press
SP  - 616
EP  - 624
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-858-5_53
DO  - 10.2991/978-94-6463-858-5_53
ID  - Sameera2025
ER  -