Auto-Expanding Fuzzy Neural Network based on Adaptative Resonance Theory for Phishing Website Detection
DOI:
https://doi.org/10.18540/jcecvl9iss8pp17142-01eKeywords:
Machine Learning, Pattern Recognition, Artificial Neural Networks, Adaptative Resonance Theory, Information SecurityAbstract
Phishing is a cyberattack based on digital fraud, the aim of which is to steal information. This problem tends to get worse due to the exponential growth in the flow of information in the digital environment, coupled with the difficulty of identifying this type of attack, since current phishing detection methods take longer than desired and often classify false negatives. Consequently, approaches using machine learning have been widely proposed, as they have the ability to detect phishing in real time and with high performance. It is in this scenario that this work is inserted, presenting the results of the detection of phishing sites via a Self-Expanding Fuzzy Neural Network based on Adaptive Resonance Theory using the "Phishing Websites Dataset" dataset available in the UCI Machine Learning Repository. The model adjusted well to the phishing problem, achieving results of 94.7% sensitivity and 92.2% accuracy.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 The Journal of Engineering and Exact Sciences
This work is licensed under a Creative Commons Attribution 4.0 International License.