VULNERABILITIES DETECTION USING MACHINE LEARNING AND CYBER SECURITY

Author Reg. ID: TIJER_108676

Published Paper Id: TIJER2309028

Published In: Volume 10 Issue 9, September-2023

Abstract: Xss attacks, SQl Injection and Online Phishing are three of the most common Internet crime techniques. Checking URLs against blacklists of known phishing websites, which are generally built based on manual verification, is a fre- quent counter measure for Phishing website Detection and is inefficient. A typical Internet User will not be able to distinguish between XSS Attack and SQL Injection Attack. As a result, as the Internet’s scale expands, technology and its components advance to give timely protection to end users. We present in this thesis an effective and versatile and malicious URL detection System with a rich collection of features that reflect many aspects of phishing webpages and their hosting platforms, as well as the detection of other vulnerabilities such as XSS Attack and SQL Injection using web scraping and a dummy code injection mechanism are used in an injection at- tack. Our system has high detection power and low error rates by Random Forest Algorithm. This is the first study that we are aware if that users effective feature col- lecting to conduct a Vulnerability Detection process of large-scale websites/URLs. The results of the experiments show that our system is capable of efficiently finding dangerous websites/URLs by the end user.

Keywords: XSS attack, SQL Injection, Online Phishing

Downloads: 000110

Page No: a204-a208

Country: Hyderabad, Telangana , India

Research Area: Science and Technology

Published Paper URL: https://tijer.org/TIJER/viewpaperforall?paper=TIJER2309028

Published Paper PDF: https://tijer.org/TIJER/papers/TIJER2309028

Click Here to Download This Article

Article Preview