•  
  •  
 

Document Type

Original Article

Abstract

Abstract: The fast spread of malicious URLs is a significant risk to online safety, since it makes assaults like spam, phishing, virus distribution, and vandalism of websites easier to carry out. The dynamic nature of these threats makes traditional detection techniques unable to keep up. Enhanced methods that can handle large-scale datasets and identify new attack patterns are needed for the real-time identification of malicious URLs. This research presents a strong hybrid machine learning approach that combines accurate classification with effective feature extraction. For feature extraction, we provide a Self-Organizing Map based Radial Movement Optimization (SOM-RMO); for classification, we present an Ensemble Radial Basis Function Network (ERBFN) optimized by Tabu Search. An RBFN tuned via Tabu Search guarantees high accuracy in the harmful URL categorization; meanwhile, the SOM-RMO efficiently performs dimensionality reduction, accentuating vital features. Our model performs better than other models in a variety of malicious URL attack scenarios. It substantially outperformed conventional detection techniques, attaining an accuracy of 97.1%, precision of 96.4%, recall of 95.8%, and an F1-score of 96.0% on a benchmark dataset.

Receive Date

14/11/2024

Revise Date

16/02/2025

Accept Date

16/02/2025

Publication Date

7-9-2025

References

[1] Mehndiratta M, Jain N, Malhotra A, Gupta I, Narula R. Malicious URL: analysis and detection using machine learning. In: 2023 10th International Conference on Computing for Sustainable Global Development (INDIACom), New Delhi, India; 2023. p. 1461e5. https://ieeexplore. ieee.org/abstract/document/10112229.

[2] Stoleriu R, Negru C, Mocanu B, Pop F. Malicious short URLs detection technique. In: 2023 22nd RoEduNet conference: networking in Education and Research (RoEduNet), Craiova, Romania; 2023. p. 1e6. https://doi.org/10.1109/RoEduNet60162.2023.10274913.

Aggarwal S. Comparative analysis of hedge funds in financial markets using machine learning models. Int J Comput Appl 2017;163(3). https://www.researchgate.net/profile/SaurabhAggarwal-15/publication/316179681_Comparative_Analysis_ of_Hedge_Funds_in_Financial_Markets_using_Machine_ Learning_Models/links/67832c3c3e33dd0be9fd12de/ Comparative-Analysis-of-Hedge-Funds-in-FinancialMarkets-using-Machine-Learning-Models.pdf.

[4] Swetha T, Seshaiah M, Hemalatha KL, Murthy SVN, BHMK. Hybrid machine learning approach for real-time malicious URL detection using SOM-RMO and RBFN with tabu search. Int J Adv Comput Sci Appl 2024;15(8). https://doi.org/ 10.14569/ijacsa.2024.0150844.

[5] Nazeeruddin E, Latif G, Mohammad N. Malicious URL detection and categorization using machine learning techniques. In: 2024 IEEE 16th international conference on Computational Intelligence and Communication Networks (CICN); 2024, December. p. 676e82. https://doi.org/10.1109/ CICN63059.2024.10847544.

[6] George Mary Nirmala, Shelly Siddharth. Energy-efficient LEACH approach employing SOM and K-means. In: 2024 IEEE recent Advances in Intelligent Computational Systems (RAICS); 2024. p. 1e6. https://doi.org/10.1109/RAICS61201. 2024.10689930.

[7] Azevedo Beatriz Flamia, Rocha Ana Maria AC, Pereira Ana I. Hybrid approaches to optimization and machine learning methods: a systematic literature review. Mach Learn 2024: 1e43. https://doi.org/10.1007/s10994-023-06467-x.

[8] Kisambu Eng KambeyL, Mjahidi Mohamedi, Kondo Tabu S. Enhancing machine learning detection technique to secure E-mail communication against malware-based phishing attacks. Int J Comput Sci Inf Secur 2024;22(3). https://zenodo. org/records/12600082.

[9] Verma Samant, Shukla Shailja. Review of fake profile classification and identification on social networks. Grenze Intern J Eng Technol (GIJET) 2024;10. https://openurl.ebsco. com/EPDB%3Agcd%3A5%3A2633909/detailv2?sid¼ebsco% 3Aplink%3Ascholar&id¼ebsco%3Agcd%3A181714936&crl¼ c&link_origin¼scholar.google.com.

[10] de la Web, Guardianes, Aprovechando el Aprendizaje Automatico para Combatir. Guardians of the web: harnessing machine learning to combat phishing attacks. 2025. https://doi.org/10.56294/gr202591.

[11] Albahadili Abbas Jabr Saleh, Akbas Ayhan, Rahebi Javad. Detection of phishing URLs with deep learning based on GAN-CNN-LSTM network and swarm intelligence algorithms. Signal, Image Video Process 2024:1e17. https://doi. org/10.1007/s11760-024-03204-2.

[12] Mai Dang Thi, Hùng NguyễnViệt. Improve the effectiveness of machine learning models in detecting website phishing using morphological features in URL analysis. J Sci Technol Informat Sec 2024:49e57. https://doi.org/10.54654/isj.v2i22. 1040.

[13] Alghenaim, Mohammed, Gamal Alkawsi, and Christopher R. Barnhart. "The state of the art in AI-based phishing detection: a systematic literature." Current Future Trends AI Applicat: Volume 1: 431, https://doi.org/10.1007/978-3-03175091-5_23.

[14] Afolabi Akindele S, Olubunmi A Akinola. Network intrusion detection using knapsack optimization, mutual information gain, and machine learning. J Elec Comput Eng 2024;2024(1): 7302909. https://doi.org/10.1155/2024/7302909.

[15] Vali M, Levente K, Gandomi AH. A new mutation operator for tabu search algorithm for continuous optimization. In: 2024 IEEE 18th international Symposium on Applied Computational Intelligence and Informatics (SACI), Timisoara, Romania; 2024. https://doi.org/10.1109/SACI60582. 2024.10619745. 000509-000514.

[16] Ghafoor Kayhan Zrar. Social bot detection using machine learning algorithms: a survey and research challenges. Polytechnic J 2023;12(2):219e28. https://doi.org/10.25156/ptj. v12n2y2022. Article 23.

[17] Hassan Sardar KH, Daneshwar Muhammadamin A. Anomaly-based network intrusion detection system using deep intelligent technique. Polytechnic J 2023;vol. 12(2): 100e13. https://doi.org/10.25156/ptj.v12n2y2022. Article 11.

[18] Zhang Z, Wang L, Zhu J, Zhu D, Gu Z, Zhang Y. MIM: a multiple integration model for intrusion detection on imbalanced samples. World Wide Web 2024;27(4):47. https:// doi.org/10.1007/s11280-024-01285-0.

[19] KL H, BHM,SVNM.Hybridmachinelearning approach for real-time malicious url detection using Som-Rmo and Rbfn with tabu search optimization. 2024. https://doi.org/10.48550/ arXiv.2407.06221.

[20] Abasi Ammar Kamal, Aloqaily Moayad, Guizani Mohsen, Ouni Bassem. Metaheuristic algorithms for 6G wireless communications: recent advances and applications. Ad Hoc Netw 2024:103474. https://doi.org/10.1016/j.adhoc.2024. 103474.

Download

Share

COinS