Algorithm for detecting malicious and legitimate URLs using support vector machines (SVM)

Authors

DOI:

https://doi.org/10.5281/zenodo.15132851

Keywords:

Artificial Intelligence, AI, Cybersecurity, Cyber threats, Support Vector Machines, SVM, Detecting attacks, Phishing, Malware

Abstract

This research examines the use of artificial intelligence (AI) in the field of cybersecurity, offering a comprehensive perspective on how advanced AI methods can enhance protection against cyber threats. The fundamentals of cybersecurity are reviewed, emphasizing their importance in safeguarding data and systems. The methodology of AI, specifically Support Vector Machines (SVM), is analyzed for its effectiveness in detecting attacks. Types of threats such as phishing and malware are also examined. To assess the practical effectiveness of these methods, experiments were conducted using public data repositories. The results indicate that SVM, among other techniques, can significantly improve the detection and response to cyber threats. This research highlights the critical role of AI in the evolution of cybersecurity and suggests future directions for research and application in this vital field.

Author Biographies

Dylan Alejandro Fernández Molina, Tecnológico de Estudios Superiores de Ecatepec

Estudiante del Tecnológico de Estudios Superiores de Ecatepec

Arturo Hernandez Martinez, Tecnológico Nacional de México/TESE de Ecatepec

Estudiante

Jimena Melendez Ramirez, Tecnológico Nacional de México/TESE de Ecatepec

Estudiante

Juan Manuel Stein Carrillo, Tecnológico Nacional de México/TESE de Ecatepec

Profesor

References

(ENISA), T. E. (17 de Abril de 2024). Artificial Intelligence and Cybersecurity Research. Obtenido de https://www.enisa.europa.eu/publications/artificial-intelligence-and-cybersecurity-research

Brunswick, U. d. (1 de Julio de 2024). URL dataset (ISCX-URL2016). Obtenido de https://www.unb.ca/cic/datasets/url-2016.html

Cybersecurity, C. I. (24 de Junio de 2024). URL dataset (ISCX-URL2016). Obtenido de http://205.174.165.80/CICDataset/ISCX-URL-2016/Dataset/

Jupyter Notebook. (12 de Junio de 2024). Obtenido de https://jupyter.org/

Matplotlib. (18 de Junio de 2024). Obtenido de https://matplotlib.org/

NumPy. (10 de Junio de 2024). Obtenido de https://numpy.org/

Pandas. (30 de Mayo de 2024). Obtenido de https://pandas.pydata.org/

Python (Oficial). (s.f.). Recuperado el 21 de Mayo de 2024, de https://www.python.org/

Scholar, S. (1 de Julio de 2024). Detecting Malicious URLs Using Lexical Analysis. Obtenido de https://www.semanticscholar.org/paper/Detecting-Malicious-URLs-Using-Lexical-Analysis-Mamun-Rathore/01bb00b24fb2bcf1d11748d0c39ba60367b4c264

Scikit-Learn. (5 de Junio de 2024). Obtenido de https://scikit-learn.org/stable/

Published

2025-04-08

How to Cite

Fernández Molina, D. A., Hernandez Martinez, A., Melendez Ramirez, J., & Stein Carrillo, J. M. (2025). Algorithm for detecting malicious and legitimate URLs using support vector machines (SVM). RICT Journal of Scientific, Technological and Innovation Research, 3(5), 32–39. https://doi.org/10.5281/zenodo.15132851