AUTOMATED DETECTION OF POTENTIALLY DANGEROUS URL ADDRESSES USING THE SCIKIT-LEARN LIBRARY
DOI:
https://doi.org/10.34185/1991-7848.itmm.2024.01.067Keywords:
dangerous URLs, phishing, scikit-learn, machine learning.Abstract
The methodology of automated detection of potentially dangerous URLs using the sci-kit-learn library is considered. The proposed methodology includes data preparation, feature generation, and model evaluation based on the random forest algorithm for classifying URLs into phishing and safe ones. The methodology is implemented using the Python programming language and the scikit-learn library. Experimental results show the effectiveness of the model in identifying potentially dangerous URLs, which plays an essential role in protecting users from fraud and other online threats.
References
INC., Webroot Threat Report. ¶[Електронний ресурс] – Режим доступу до ресурсу: https : / / www - cdn . webroot . com.
Sheng, Steve, Brad Wardman, Gary Warner, Lorrie Faith Cranor, Jason I. Hong and Chengshan Zhang. “An Empirical Analysis of Phishing Blacklists.” International Conference on Email and Anti-Spam, 2009.
J. H. Ateeq and M. Moreb, “Detecting malicious URL using neural network”, in Proc. Int. Congr. Adv. Technol. Eng. (ICOTEN), Jul. 2021, pp. 1–8.
M. E. H. V. S. Aalla and N. R. Dumpala, “Malicious URL prediction using machine learning techniques”, Ann. Romanian Soc. Cell Biol., vol. 25, no. 5, pp. 2170–2176, 2021.
Y. Pingle, S. N. Bhatkar, and S. Patil, “Detection of malicioius content using AI”, in Proc. 7th Int. Conf. Computing Sustain. Global Develop., 2020, pp. 1–6.
