Paper Key : IRJ************895
Author: Sanika S. Ambadkar,Shraddha M. Deshmukh,Dhanashree J. Agham,Anuj S. Mahure,Kalyani H. Deshmukh
Date Published: 15 Apr 2024
Abstract
Malicious URLs are links that when clicked, direct users to a web page or website that could be potentially hazardous or fraudulent. As the name suggests, a malicious URL never leads to anything good. The issue of cybersecurity is widespread because it has the ability to steal sensitive information and cause financial losses. Viruses such as phishing, spam, drive-by vulnerabilities, and other unwanted content are hosted on malicious URLs. Typically, a data breach will cost $4.24 million. Detecting and responding to such threats as soon as possible is of utmost importance as a result of this. The main tool used for detection in the past has been blacklists. However, blacklists are incomplete and unable to identify recently created harmful URLs. The generality of malicious URL detectors has been improved through the use of machine learning techniques. The goal of this study is to provide a comprehensive survey and a structural understanding of the methods used to detect harmful URLs using machine learning. A different approach to problem solving and machine learning approaches that yield a more accurate result are presented. The use of random forest and support vector machine algorithms is a popular approach when dealing with malicious URLs. Additionally, this paper provides a timely and comprehensive review of different strategies to tackle this issue in the cybersecurity industry, including coverage for future research.
DOI Requested