Abstract—The rapid growth of internet has created many
services, which have become an integral part of our day in
today life by using Web applications for making reservations,
paying bills, and shopping on-line.
The vulnerabilities in web application code provide an opportunity to the attack to be entre on applications level. Most network firewalls and antivirus software programs cannot stop attacks at the application level.
In this paper, we have developed a prototypic web application firewall to detect new types of attacks that do not require signature updates, using a neural network back-propagation approach for identifying attacks that were not detected at the stage of signature analysis.
The solution has been experimented on some parameters and some additional information about the user behaviors when the user accesses the web application and makes application-level control of the firewall in the framework of the scope of the WEB-application.
The system is found to have good performance in comparing and matching the test patterns with already stored patterns and from (24) test data, (95%) success rate have been correctly recognized.
Index Terms—Web applications firewall, signature, artificial neural network.
The authors are with Iraqi Commission for Computers and Informatics, Ministry of Higher Education and Scientific Research, Iraq (e-mail: firstname.lastname@example.org, Sahab7dia@yahoo.com, email@example.com).
Cite: Jane Jaleel Stephan, Sahab Dheyaa Mohammed, and Mohammed Khudhair Abbas, "Neural Network Approach to Web Application Protection," International Journal of Information and Education Technology vol. 5, no. 2, pp. 150-155, 2015.