Detection and Prevention of SQL Injection Attacks at Runtime Using Decision Tree Classification

The use of web applications has become increasingly popular in our routine activities, such as reading the news, paying bills, and shopping on-line. As the availability of these services grows, we are witnessing an increase in the number and sophistication of attacks that target web applications. SQL injection attacks are a serious security threat to web applications in the cyberspace. SQL injection attacks allow attackers to gain unlimited access to a database that includes applications and potentially sensitive information. Although researchers and practitioners have proposed different methods to solve the SQL injection problem, current approaches either fail to solve the full scope of the problem or have limitations that prevent their use and adoption. This study is designed to provide a method for detecting and preventing SQL injection attacks at runtime, which can detect and continuously monitor the existing and new attacks. The proposed detection and prevention method by runtime monitoring and implementation of the decision tree classification on the SQL injection database, blocks existing SQL injection attacks and also detects new attacks using the database supervisor. In the end, the proposed method is compared with other methods for detecting and preventing existing SQL injection attacks, the results showing that the proposed method is significantly successful in detecting and preventing SQL injection attacks. Compared to the two methods explored in this article, the presented method increases the accuracy by 12% for one method and 16% for the other.