SQL Injection Attack Detection using Machine Learning Algorithms

Laila Aburashed; Marah AL Amoush; Wardeh Alrefai

doi:10.37934/sijml.2.1.112

Authors

Laila Aburashed Department of Cyber Security, Faculty of information Technology, Zarqa Technical Intermediate Collage, Zarqa, Jordan
Marah AL Amoush Department of Cyber Security, Faculty of information Technology, Zarqa Technical Intermediate Collage, Zarqa, Jordan
Wardeh Alrefai Department of Cyber Security, Faculty of information Technology, Zarqa Technical Intermediate Collage, Zarqa, Jordan

DOI:

https://doi.org/10.37934/sijml.2.1.112

Keywords:

SQL- injection, machine learning, Random Forest, ANN, datasets, Gradient Boosting, SVM

Abstract

SQL Injection is one of the most common vulnerabilities exploited for both privacy breaches and financial damage. It remains the top vulnerability on the most recent OWASP Top 10 list, with the number of such attacks on the rise. The SQL Injection Detection Challenge is addressed using machine learning algorithms. By employing a classification method, communications are identified as either SQL Injection or plain text. This research proposes a machine learning framework to assess the feasibility of using a machine learning classifier to detect SQL Injection attacks. Classification algorithms such as Random Forest, Gradient Boosting, SVM, and ANN are utilized. As a result, ANN demonstrated superior performance and required less time to detect SQL Injection attacks.