Comparative Analysis of Various Machine Learning Techniques for Detecting Malicious Webpages
Gayaksha Kandolkar, Soniya Usgaonkar · Zenodo (CERN European Organization for Nuclear Research) · 2021
Due to the rapid growth of the internet, websites have become the intruder's main target. Malicious websites, when visited by an unsuspecting victim infect their machine to steal valuable information, redirect them to malicious targets or compromise their system to mount future attack. At times a malicious dynamic HTML code is usually embedded in a normal webpage. Anti-virus software packages commonly use signature-based approaches which might not be able to efficiently identify camouflaged malicious HTML codes. Therefore, using machine learning approach to detect malicious web content is a better alternative. The objective of this project is to train various machine learning classifier models on the dataset created to predict malicious websites. The study is also conducted to measure and compare the performance level of these machine learning classifiers.