Comparative Analysis of Different Machine Learning Models with Different Phishing Datasets
Bhavagna Gadde, Anisha Pothineni, Akhileswar Vathaluru, Baba Afrid, Sandeep Kumar, Munish Kumar · 2024
Phishing attacks, a significant problem on the internet, trick people into giving away sensitive information. Our research aims to find effective ways to prevent these attacks using computer programs that learn from data. We're using two sets of information to train these programs: Mendeley phishing data and Kaggle phishing data. Our study focuses on getting the data ready, identifying important details, and determining if something is a phishing attempt. We're testing various approaches with these computer programs and comparing them to determine which works best with our information. This research is dedicated to discovering more robust methods to safeguard people from the growing threat of phishing attacks online. By delving into the intricacies of data preprocessing, classification algorithms, and hybrid models, our study seeks to unravel the adaptability of machine learning models to diverse phishing scenarios. Through rigorous analysis, we aim to contribute valuable insights that advance the development of proactive cybersecurity measures against the dynamic and evolving landscape of phishing threats on the internet.