Publications

@article{martinez-mendoza_applying_2023,

title = {Applying Machine Learning to login URLs for phishing detection},

author = {Alicia Martínez-Mendoza and Manuel Sánchez-Paniagua and Andrés Carofilis-Vasco and Francisco Jáñez-Martino and Eduardo Fidalgo and Enrique Alegre},

url = {https://dialnet.unirioja.es/servlet/articulo?codigo=9044941},

year  = {2023},

date = {2023-01-01},

journal = {Actas de las VIII Jornadas Nacionales de Investigación en Ciberseguridad: Vigo, 21 a 23 de junio de 2023},

pages = {487–488},

abstract = {This paper explores the application of machine learning for phishing detection using login URLs. By analyzing URL patterns and features, the study aims to differentiate between legitimate and phishing websites. Various machine learning models are evaluated to enhance detection accuracy, providing a proactive approach to cybersecurity threats.},

note = {Publisher: Universidade de Vigo},

keywords = {AI, Cybersecurity, machine learning, phishing detection, URL analysis},

pubstate = {published},

tppubtype = {article}

}

@article{sanchez-paniagua_phishing_2022-1,

title = {Phishing URL detection: A real-case scenario through login URLs},

author = {Manuel Sánchez-Paniagua and Eduardo Fidalgo and Enrique Alegre and Wesam Al-Nabki and Víctor González-Castro},

url = {https://ieeexplore.ieee.org/abstract/document/9759382},

year  = {2022},

date = {2022-01-01},

journal = {IEEE Access},

volume = {10},

pages = {42949–42960},

abstract = {This paper compares machine learning and deep learning techniques to detect phishing websites through URL analysis. Unlike most current methods, which use only homepages, this study includes URLs from login pages for both legitimate and phishing websites, providing a more realistic scenario. It also demonstrates that existing techniques have high false-positive rates when tested on URLs from legitimate login pages. The authors create a new dataset, Phishing Index Login URL (PILU-90K), and show how older models decrease in accuracy over time. A Logistic Regression model with TF-IDF feature extraction achieves 96.50% accuracy on the login URL dataset.},

note = {Publisher: IEEE},

keywords = {Dataset Creation, machine learning, phishing detection, URL analysis},

pubstate = {published},

tppubtype = {article}

}