Penerapan Soft Voting Ensemble Berbasis LightGBM, XGBoost, dan CatBoost untuk Deteksi Website Phishing Berdasarkan Fitur URL dan Domain
Abstract
Phishing websites are crafted to resemble legitimate services in order to obtain user credentials and other sensitive information. Blacklist-based mechanisms frequently fail to recognise newly emerging sites, while high reported accuracy remains insufficient to characterise operational risk, since misclassifying a malicious site as legitimate carries a greater consequence than the opposite error. This study applies a Soft Voting Ensemble method that combines the class probabilities of LightGBM, XGBoost, and CatBoost, and compares it against individual models, a Stacking Ensemble, and a Multilayer Perceptron. The evaluation employs a public dataset comprising 11,055 instances and 30 predictive features describing URL, domain, certificate, and page content characteristics, with phishing designated as the positive class. Median imputation and MinMax scaling were placed within a pipeline to mitigate data leakage, after which the data were divided using a stratified 90:10 split. Model performance was assessed on the test set as well as through stratified five-fold cross-validation. On the test set, XGBoost attained the highest accuracy of 98.01% with a phishing F1-score of 97.73%, whereas Soft Voting reached 97.83% accuracy and a phishing F1-score of 97.52%, with 472 true positives, 18 false negatives, 6 false positives, and 610 true negatives. Under cross-validation, Soft Voting recorded the highest mean accuracy of 97.25% and mean phishing F1-score of 96.86%. These findings indicate that model superiority may shift as the evaluation scheme changes. The principal contribution lies in a consistent and traceable evaluation design, so that small performance margins are not readily interpreted as generally valid superiority.
Downloads
References
Anti-Phishing Working Group, “Phishing Activity Trends Report: 1st Quarter 2026,” Cambridge, MA, USA, May 2026. Accessed: Aug. 26, 2026. [Online]. Available: https://docs.apwg.org/reports/apwg_trends_report_q1_2026.pdf
ENISA Threat Landscape 2025, “European Union Agency for Cybersecurity,” Athens, Greece, Oct. 2025. doi: 10.2824/2445233.
E. Kytidou, T. Tsikriki, G. Drosatos, and K. Rantos, “Machine learning techniques for phishing detection: A review of methods, challenges, and future directions,” Intelligent Decision Technologies, vol. 19, no. 6, pp. 4356–4379, Nov. 2025, doi: 10.1177/18724981251366763.
G. S. Nayak, B. Muniyal, and M. C. Belavagi, “Enhancing Phishing Detection: A Machine Learning Approach With Feature Selection and Deep Learning Models,” IEEE Access, vol. 13, pp. 33308–33320, 2025, doi: 10.1109/ACCESS.2025.3543738.
N. Yadav and S. P. Panda, “Feature Selection for Email Phishing Detection Using Machine Learning,” 2022, pp. 365–378. doi: 10.1007/978-981-16-2597-8_31.
A. Awasthi and N. Goel, “Phishing website prediction using base and ensemble classifier techniques with cross-validation,” Cybersecurity, vol. 5, no. 1, p. 22, Nov. 2022, doi: 10.1186/s42400-022-00126-9.
T. M. Bao, K. Shashvat, N. G. Nhu, and D.-N. Le, “A Comparative Analysis of Machine Learning Algorithms for Spam and Phishing URL Classification,” Computers, Materials & Continua, vol. 87, no. 2, pp. 1–10, 2026, doi: 10.32604/cmc.2025.075161.
N. Innab et al., “Phishing Attacks Detection Using Ensemble Machine Learning Algorithms,” Computers, Materials & Continua, vol. 80, no. 1, pp. 1325–1345, 2024, doi: 10.32604/cmc.2024.051778.
H. Fadhilah, D. R. Maulana, and R. Utari, “Tree-based Ensemble Machine Learning for Phishing Website Detection,” Komputika : Jurnal Sistem Komputer, vol. 13, no. 2, pp. 233–243, Oct. 2024, doi: 10.34010/komputika.v13i2.12495.
A. A. Albishri and M. M. Dessouky, “A Comparative Analysis of Machine Learning Techniques for URL Phishing Detection,” Engineering, Technology & Applied Science Research, vol. 14, no. 6, pp. 18495–18501, Dec. 2024, doi: 10.48084/etasr.8920.
A. Jain et al., “PhishNet 1.0: optuna-optimized stacking ensemble with Boruta-based feature selection for phishing URL detection,” Sci. Rep., vol. 16, no. 1, p. 1480, Dec. 2025, doi: 10.1038/s41598-025-31447-7.
M. Bahaghighat, M. Ghasemi, and F. Ozen, “A high-accuracy phishing website detection method based on machine learning,” Journal of Information Security and Applications, vol. 77, p. 103553, Sep. 2023, doi: 10.1016/j.jisa.2023.103553.
P. Bountakas and C. Xenakis, “HELPHED: Hybrid Ensemble Learning PHishing Email Detection,” Journal of Network and Computer Applications, vol. 210, p. 103545, Jan. 2023, doi: 10.1016/j.jnca.2022.103545.
C. Opara, Y. Chen, and B. Wei, “Look before you leap: Detecting phishing web pages by exploiting raw URL and HTML characteristics,” Expert Syst. Appl., vol. 236, p. 121183, Feb. 2024, doi: 10.1016/j.eswa.2023.121183.
A. Prasad and S. Chandra, “PhiUSIIL: A diverse security profile empowered phishing URL detection framework based on similarity index and incremental learning,” Comput. Secur., vol. 136, p. 103545, Jan. 2024, doi: 10.1016/j.cose.2023.103545.
M. Hussain, C. Cheng, R. Xu, and M. Afzal, “CNN-Fusion: An effective and lightweight phishing detection method based on multi-variant ConvNet,” Inf. Sci. (N. Y)., vol. 631, pp. 328–345, Jun. 2023, doi: 10.1016/j.ins.2023.02.039.
N. Q. Do, A. Selamat, H. Fujita, and O. Krejcar, “An integrated model based on deep learning classifiers and pre-trained transformer for phishing URL detection,” Future Generation Computer Systems, vol. 161, pp. 269–285, Dec. 2024, doi: 10.1016/j.future.2024.06.031.
S. Mousavi and M. Bahaghighat, “Phishing Website Detection: An In‐Depth Investigation of Feature Selection and Deep Learning,” Expert Syst., vol. 42, no. 3, Mar. 2025, doi: 10.1111/exsy.13824.
Z. Salah, H. Abu Owida, E. Abu Elsoud, E. Alhenawi, S. Abuowaida, and N. Alshdaifat, “An Effective Ensemble Approach for Preventing and Detecting Phishing Attacks in Textual Form,” Future Internet, vol. 16, no. 11, p. 414, Nov. 2024, doi: 10.3390/fi16110414.
M. N. Yeasmin, M. A. R. Refat, B. C. Singh, Z. Alom, Z. Aung, and M. Azim, “EnLeM: ensemble learning-based model to detect phishing websites,” EURASIP J. Inf. Secur., vol. 2026, no. 1, p. 1, Dec. 2025, doi: 10.1186/s13635-025-00219-1.
M. Agagu, I. A. Ogunbiyi, A. Lasisi, and O. Omorogiuwa, “Detection of Phishing Websites from URLs Using Hybrid Ensemble-Based Machine Learning Technique,” 2024, pp. 11–22. doi: 10.1007/978-3-031-66965-1_2.
Z. Alamri, A. Alhuzali, B. Alsulami, and D. Alghazzawi, “Enhanced Phishing Website Detection Using Optimized Ensemble Stacking Models,” International Journal of Advanced Computer Science and Applications, vol. 16, no. 8, 2025, doi: 10.14569/IJACSA.2025.01608100.
D. R. Patil, T. M. Pattewar, T. S. Shinde, K. S. Kumavat, and S. N. Deshpande, “Stacking and Voting-Based Boosting Ensembles for Robust Malicious URL Classification,” Informatica, vol. 49, no. 35, Dec. 2025, doi: 10.31449/inf.v49i35.7762.
R. S. Rao, C. Kondaiah, A. R. Pais, and B. Lee, “A hybrid super learner ensemble for phishing detection on mobile devices,” Sci. Rep., vol. 15, no. 1, p. 16839, May 2025, doi: 10.1038/s41598-025-02009-8.
A. Géron, Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 3rd ed. Sebastopol, CA, USA: O’Reilly Media, 2022.
C. Chio and D. Freeman, Machine Learning and Security: Protecting Systems with Data and Algorithms. Sebastopol, CA, USA: O’Reilly Media, 2018.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Penerapan Soft Voting Ensemble Berbasis LightGBM, XGBoost, dan CatBoost untuk Deteksi Website Phishing Berdasarkan Fitur URL dan Domain
Pages: 213-222
Copyright (c) 2026 Rozan Sanura Albary

This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).







