Authors :
Vaishali Bhargava; Sharvan Kumar Garg
Volume/Issue :
Volume 8 - 2023, Issue 9 - September
Google Scholar :
https://tinyurl.com/25f6xzne
Scribd :
https://tinyurl.com/3pyp984p
DOI :
https://doi.org/10.5281/zenodo.8437510
Abstract :
Phishing attacks, which target users through
fraudulent websites and emails to steal critical
information, continue to pose a significant danger to
internet security. Traditional ways of detecting phishing
websites frequently fall behind the shifting tactics used by
fraudsters. Machine learning approaches are being used
as a powerful tool for improving phishing detection
capabilities in this kind of context. The current study
investigates a novel Machine Learning Model for
Detecting Phishing Websites that employ advanced
algorithms and feature selection methodologies.Through a rigorous
experimental approach, the study evaluates their
performance using key metrics including accuracy,
precision, and recall.Conversely, when the data was split 50-50,
Random Forest yielded better results.
Keywords :
Phishing; Classification; Decision Tree; Machine Learning; Cyber Security.
Phishing attacks, which target users through
fraudulent websites and emails to steal critical
information, continue to pose a significant danger to
internet security. Traditional ways of detecting phishing
websites frequently fall behind the shifting tactics used by
fraudsters. Machine learning approaches are being used
as a powerful tool for improving phishing detection
capabilities in this kind of context. The current study
investigates a novel Machine Learning Model for
Detecting Phishing Websites that employ advanced
algorithms and feature selection methodologies.Through a rigorous
experimental approach, the study evaluates their
performance using key metrics including accuracy,
precision, and recall.Conversely, when the data was split 50-50,
Random Forest yielded better results.
Keywords :
Phishing; Classification; Decision Tree; Machine Learning; Cyber Security.
