A System to Detect and Block SQL Injection with the help of Multi Agent System using Artificial Neural Network

Abstract

This paper describes a Multi agent system which uses Artificial Neural Network algorithm, which helps to detect malicious SQL queries. As SQL injection queries are one of the most hazardous attacks for database security in today's database system, this multi agent system is useful to catch SQL injection attacks. This system possesses a multi level architecture which uses multiple agents, where each level is assigned with some. The SQL injection attacks are one of the biggest security threats in databases. SQL injection is a technique used to take advantage of non-validated input vulnerabilities to pass SQL commands through a Web application for execution by a back-end database. This system checks each query rigorously and goes through idCBR cycle i.e case based reasoning is done which gives the output legal/illegal/suspicious.