Mitigation of SQL Injection Attacks Through Machine Learning Classifier

The security of sensitive data stored in web databases is a growing issue, despite the fact that online-based services are becoming an indispensable part of our daily lives. SQL injection attacks have been a frequent and pervasive security problem for web applications for the last few decades. Attackers have used this vulnerability to cause massive data breaches. The issue is more concerning than it has ever been because of automated and sophisticated attack methods. Although there has been a lot of research on SQL injection attack mitigation, the threat has essentially not changed. The evolution of SQL injection attack vectors, which now include new traits and forms, has made the problem considerably more challenging. This study analyzes the technical details of the problem, perform a comprehensive literature study, and develop machine learning paradigm-based solutions for SQL injection attack detection. Moreover, the proposed method employs variety of machine learning techniques available on the Kaggle dataset, including KNN Classifier, Random Forest, Voting Classifier, Perceptron + SGD and Logistic Regression to identify and find SQL Injection attacks.