Innovative Framework for SQL Injection Defence: Leveraging Machine Learning and Hybrid Approaches for Enhanced Detection and Prevention
Aryan Prajapati Prajapati
Paper Contents
Abstract
A web application is a software system that provides users with an interface through a web browser, accessible on any operating system. Despite their increasing popularity, web applications are becoming more vulnerable to a wide range of security threats, often resulting in severe consequences. One of the most prevalent threats is malware attacks, particularly SQL injection (SQLI) attacks, which are commonly found in poorly designed web applications.SQLI vulnerabilities have been a known security risk for over two decades and remain a significant concern. Over the years, various techniques have been proposed to mitigate SQLI attacks; however, most fail to comprehensively address the issue. SQLI is one of the most dangerous web-based attacks, allowing attackers to modify, delete, read, or duplicate data from database servers. A successful SQLI attack can compromise all aspects of security, including confidentiality, data integrity, and availability.This paper explores common SQLI attack patterns, their underlying mechanisms, and effective methods for identifying, detecting, and preventing them based on SQL query analysis.
Copyright
Copyright © 2025 Aryan Prajapati. This is an open access article distributed under the Creative Commons Attribution License.