Optimization of Boosting-based Classification for Phishing Web Detection Using Ant Colony Optimization

Kadek Adies Wiranegara; Dandy Pramana Hostiadi; Roy Rudolf Huizen

doi:10.29407/intensif.v10i2.28480

Authors

Kadek Adies Wiranegara Institut Teknologi dan Bisnis STIKOM Bali https://orcid.org/0009-0000-7199-2332
Dandy Pramana Hostiadi Institut Teknologi dan Bisnis STIKOM Bali https://orcid.org/0000-0003-0096-8049
Roy Rudolf Huizen Institut Teknologi dan Bisnis STIKOM Bali https://orcid.org/0000-0002-3671-6030

DOI:

https://doi.org/10.29407/intensif.v10i2.28480

Keywords:

Phishing Detection, Boosting Algorithms, Ant Colony Optimization, Feature Selection, Machine Learning

Abstract

Background: Cybercriminals commonly use phishing attacks by manipulating domain and website characteristics to mislead users into revealing sensitive personal information. The increasing scale of phishing attacks demands automated detection mechanisms that are accurate, efficient, and reproducible. Objective: The purpose of this research is to compare and evaluate the performance of boosting-based machine learning models for phishing domain detection integrated with Ant Colony Optimization (ACO) for feature selection. This study also aims to analyze the impact of ACO-based feature selection on classification performance and feature efficiency under consistent experimental conditions. Methods: Experiments were conducted using a public phishing webpage dataset from Kaggle, comprising 11,430 samples and 87 numerical features extracted from URL structures and webpage characteristics. Two scenarios were evaluated: training models with all features and with a reduced feature subset selected by ACO. Performance was assessed using Accuracy, Precision, Recall, F1-score, and ROC–AUC under a fixed train–test split and predefined hyperparameters. Result: Experimental results showed that LightGBM without feature selection achieved the highest accuracy 97.24%. However, ACO reduced feature dimensionality and improved computational efficiency in some models, including faster execution and lower memory usage for LightGBM, while also slightly decreasing accuracy. These findings indicate that ACO effectiveness is model-dependent and involves a balance between predictive performance and computational efficiency. Conclusion: The results confirm that boosting-based models effectively detect phishing domains, while ACO showed model-dependent effects on feature efficiency and computational trade-offs. Future work should use diverse datasets and systematic hyperparameter optimization to improve generalizability and performance.

Downloads

Download data is not yet available.

Abstract views: 18 , PDF downloads: 11

References

[1] L. Gallo, D. Gentile, S. Ruggiero, A. Botta, and G. Ventre, “The human factor in phishing: Collecting and analyzing user behavior when reading emails,” Comput. Secur., vol. 139, p. 103671, Apr. 2024, doi: 10.1016/j.cose.2023.103671.

[2] S. J. M. S. Al-Naimi, A. Sadighian, and G. Oligeri, “User Behavior Under Phishing Attacks: Eye tracking, Scenarios and Analysis,” in 2025 10th International Conference on Information and Network Technologies (ICINT), IEEE, Mar. 2025, pp. 9–16. doi: 10.1109/ICINT65528.2025.11030908.

[3] R. K. Ayeni, A. A. Adebiyi, J. O. Okesola, and E. Igbekele, “Phishing Attacks and Detection Techniques: A Systematic Review,” in 2024 International Conference on Science, Engineering and Business for Driving Sustainable Development Goals (SEB4SDG), IEEE, Apr. 2024, pp. 1–17. doi: 10.1109/SEB4SDG60871.2024.10630203.

[4] A. S. I. S. - et al., “Understanding the Impact of Phishing Attacks on Organizational Security and Trust,” International Journal For Multidisciplinary Research, vol. 6, no. 6, Dec. 2024, doi: 10.36948/ijfmr.2024.v06i06.34230.

[5] W. Li, S. Manickam, Y.-W. Chong, W. Leng, and P. Nanda, “A State-of-the-Art Review on Phishing Website Detection Techniques,” IEEE Access, vol. 12, pp. 187976–188012, 2024, doi: 10.1109/ACCESS.2024.3514972.

[6] D. Komalasari, T. B. Kurniawan, D. A. Dewi, M. Z. Zakaria, Z. Abdullah, and A. Alanda, “Phishing Domain Detection Using Machine Learning Algorithms,” Int. J. Adv. Sci. Eng. Inf. Technol., vol. 15, no. 1, pp. 318–327, Feb. 2025, doi: 10.18517/ijaseit.15.1.12553.

[7] H. Ghalechyan, E. Israyelyan, A. Arakelyan, G. Hovhannisyan, and A. Davtyan, “Phishing URL detection with neural networks: an empirical study,” Sci. Rep., vol. 14, no. 1, p. 25134, Dec. 2024, doi: 10.1038/s41598-024-74725-6.

[8] S. S. Kumar, P. Muthusamy, and M. P. A. Jerald, “A Hybrid Framework for Improved Weighted Quantum Particle Swarm Optimization and Fast Mask Recurrent CNN to Enhance Phishing-URL Prediction Performance,” International Journal of Computational Intelligence Systems, vol. 17, no. 1, Dec. 2024, doi: 10.1007/s44196-024-00663-w.

[9] M. A. Daniel, S.-C. Chong, L.-Y. Chong, and K.-K. Wee, “Optimising Phishing Detection: A Comparative Analysis of Machine Learning Methods with Feature Selection,” Journal of Informatics and Web Engineering, p., 2025, doi: 10.33093/jiwe.2025.4.1.15.

[10] F. Karimi, M. B. Dowlatshahi, and A. Hashemi, “SemiACO: A semi-supervised feature selection based on ant colony optimization,” Expert Syst. Appl., vol. 214, p. 119130, Mar. 2023, doi: 10.1016/j.eswa.2022.119130.

[11] S. Jungjit, A. Prasitsupparote, S. S. Nathan, and T. Rattanakietkhajorn, “Ant Colony Optimization for Multi-Label Correlation-based Feature Selection Method,” in 2025 Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunications Engineering (ECTI DAMT & NCON), IEEE, Jan. 2025, pp. 797–802. doi: 10.1109/ECTIDAMTNCON64748.2025.10961959.

[12] 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.

[13] M. K. Prabhakaran, A. D. Chandrasekar, and P. Meenakshi Sundaram, “PHISH_ATTENTION: achieving robust phishing website detection with balanced datasets and advanced URL features,” Comput. J., vol. 68, no. 9, pp. 1263–1284, Sep. 2025, doi: 10.1093/comjnl/bxaf036.

[14] A. Safi and S. Singh, “A systematic literature review on phishing website detection techniques,” Journal of King Saud University - Computer and Information Sciences, vol. 35, no. 2, pp. 590–611, Feb. 2023, doi: 10.1016/j.jksuci.2023.01.004.

[15] M. K. Dahouda and I. Joe, “A Deep-Learned Embedding Technique for Categorical Features Encoding,” IEEE Access, vol. 9, pp. 114381–114391, 2021, doi: 10.1109/ACCESS.2021.3104357.

[16] M. A. Lones, “Avoiding common machine learning pitfalls,” Patterns, vol. 5, no. 10, p. 101046, Oct. 2024, doi: 10.1016/j.patter.2024.101046.

[17] S. Shahidi, A. Wahid Samadzai, and H. Shahbazi, “Effective Data Preprocessing in Data Science: From Method Selection to Domain-Specific Optimization,” Journal of Advanced Computer Knowledge and Algorithms, vol. 2, no. 4, pp. 84–90, Jul. 2025, doi: 10.29103/jacka.v2i4.22886.

[18] B. Bala and S. Behal, “A Brief Survey of Data Preprocessing in Machine Learning and Deep Learning Techniques,” in 2024 8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC), IEEE, Oct. 2024, pp. 1755–1762. doi: 10.1109/I-SMAC61858.2024.10714767.

[19] U. Sarmah, P. Borah, and D. K. Bhattacharyya, “Ensemble Learning Methods: An Empirical Study,” SN Comput. Sci., vol. 5, no. 7, p. 924, Oct. 2024, doi: 10.1007/s42979-024-03252-y.

[20] I. G. A. P. Mahendra, I. M. A. Wirawan, and I. G. A. Gunadi, “Enhancement performance of the Naïve Bayes method using AdaBoost for classification of diabetes mellitus dataset type II,” International Journal of Advances in Applied Sciences, vol. 13, no. 3, p. 733, Sep. 2024, doi: 10.11591/ijaas.v13.i3.pp733-742.

[21] I. AlShourbaji, N. Helian, Y. Sun, A. G. Hussien, L. Abualigah, and B. Elnaim, “An efficient churn prediction model using gradient boosting machine and metaheuristic optimization,” Sci. Rep., vol. 13, no. 1, p. 14441, Sep. 2023, doi: 10.1038/s41598-023-41093-6.

[22] M. ZLOBIN and V. BAZYLEVYCH, “BAYESIAN OPTIMIZATION FOR TUNING HYPERPARAMETRS OF MACHINE LEARNING MODELS: A PERFORMANCE ANALYSIS IN XGBOOST,” Computer systems and information technologies, no. 1, pp. 141–146, Mar. 2025, doi: 10.31891/csit-2025-1-16.

[23] P. R, S. Obbayed, K. Manju, G. Swarnalakshmi, and N. Purushotham, “Employee Attrition Prediction based on Light Gradient Boosting Machine with Bayesian Optimization,” in 2025 International Conference on Intelligent Systems and Computational Networks (ICISCN), IEEE, Jan. 2025, pp. 1–5. doi: 10.1109/ICISCN64258.2025.10934683.

[24] H. Wu, Y. Mao, J. Weng, Y. Yu, and J. Wang, “Fractional light gradient boosting machine ensemble learning model: A non-causal fractional difference descent approach,” Information Fusion, vol. 118, p. 102947, Jun. 2025, doi: 10.1016/j.inffus.2025.102947.

[25] Z. Zeng, “Enhancing Data Science Salary Prediction through CatBoost-Integrated Ensemble Learning: A Comparative Study of Gradient Boosting Methods,” in 2025 International Conference on Computers, Information Processing and Advanced Education (CIPAE), IEEE, Aug. 2025, pp. 197–203. doi: 10.1109/CIPAE66821.2025.00040.

[26] S. Rallapalli and Y. M. Mahendra Kumar, “Optimizing Employee Promotion Decisions: A Novel Machine Learning Framework for Predictive Analysis by using GBM CatBoost,” in 2024 First International Conference on Software, Systems and Information Technology (SSITCON), IEEE, Oct. 2024, pp. 1–7. doi: 10.1109/SSITCON62437.2024.10796145.

[27] Y. F. Zamzam, T. H. Saragih, R. Herteno, Muliadi, D. T. Nugrahadi, and P. H. Huynh, “Comparison of CatBoost and Random Forest Methods for Lung Cancer Classification using Hyperparameter Tuning Bayesian Optimization-based,” Journal of Electronics, Electromedical Engineering, and Medical Informatics, vol. 6, no. 2, pp. 125–136, Apr. 2024, doi: 10.35882/jeeemi.v6i2.382.

[28] M. Ghosh, R. Guha, R. Sarkar, and A. Abraham, “A wrapper-filter feature selection technique based on ant colony optimization,” Neural Comput. Appl., vol. 32, no. 12, pp. 7839–7857, Jun. 2020, doi: 10.1007/s00521-019-04171-3.

[29] K. Nemati, A. Sheikhani, S. Kordrostami, and K. Khoshhal, “The embedded feature selection method using ANT colony optimization with structured sparsity norms,” Computing, vol. 107, Dec. 2024, doi: 10.1007/s00607-024-01387-7.

[30] T. Reznychenko, E. Uglickich, and I. Nagy, “Categorical Model Estimation with Feature Selection Using an Ant Colony Optimization,” in Proceedings of the 22nd International Conference on Informatics in Control, Automation and Robotics, SCITEPRESS - Science and Technology Publications, 2025, pp. 219–226. doi: 10.5220/0013705300003982.

[31] O. Rainio, J. Teuho, and R. Klén, “Evaluation metrics and statistical tests for machine learning,” Sci. Rep., vol. 14, no. 1, p. 6086, Mar. 2024, doi: 10.1038/s41598-024-56706-x.

[32] O. Kyrsanov and S. Kryvenko, “Machine learning model for predicting substance properties based on its physicochemical properties,” INNOVATIVE TECHNOLOGIES AND SCIENTIFIC SOLUTIONS FOR INDUSTRIES, no. 1(31), pp. 151–165, Mar. 2025, doi: 10.30837/2522-9818.2025.1.151.

[33] R. Alzubi, T. Bishtawi, and H. Kassem, “Improving Web Security through Machine Learning: A Feature-Based Methodology for Detecting Phishing URLs,” Engineering, Technology & Applied Science Research, vol. 15, no. 5, pp. 26845–26851, Oct. 2025, doi: 10.48084/etasr.12015.

[34] A. Hannousse and S. Yahiouche, “Towards benchmark datasets for machine learning based website phishing detection: An experimental study,” Eng. Appl. Artif. Intell., vol. 104, Sep. 2021, doi: 10.1016/j.engappai.2021.104347.