An Experimental setup for Detecting SQLi Attacks using Machine Learning Algorithms

Authors

  • Binh An Pham West Texas A&M University
  • Vinitha Hannah Subburaj West Texas A&M University

Keywords:

cybersecurity, SQL injection attacks, machine learning algorithms

Abstract

SQL injection attacks (SQLi attacks) have proven their danger on several website types such as social media, e-shopping, etc... In order to prevent such attacks from occurring, this research effort investigates on efficient ways of detection and prevention, so that we can preserve each cyber-user’s right of privacy. This research effort is aimed at investigating and looking at different ways to protect websites from SQL injection attacks. In this research effort, machine learning algorithms were used to detect such SQLi attacks. Machine Learning (ML) algorithms are algorithms that can learn from the data provided and infer interesting results from the dataset. We used SQL code and user input as our data and ML algorithms to detect malicious code. The machine learning model developed in this research can detect such attacks from happening in future. The precision and accuracy of the machine learning algorithms in terms of predicting the SQLi attacks has been calculated and reported in this research paper.

Downloads

Published

2020-12-01