Malicious Attack Detector

Computer Science and Engineering

The taint URLs guide the client to suspicious websites which collects the users invaluable information and exploit their system. Here we propose an authentication based approach to detect such websites. We developed a tool called Analyzer an enhanced browser prevent the user from malicious attack. It analyze the website using EWLSVM (Ehnanced Weighted Least Square Twin Support Vector Machine) machine learning algorithm to find the website is malicious or not. The proposed approach is compared with existing approaches which reports low false positive and false negative. The experimental approach shows the proposed approach correctly detects all phishing and genuine website without any false positive and negatives. It overcomes many drawback of the existing signature based approaches

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.