Machine Learning-Based Detection and Classification of SQL Injection Attacks Using a Stacking Ensemble Model

Abstract

SQL injection attacks pose a significant risk to web applications because they can grant unauthorized access to databases and private information. The purpose of this study is to detect and classify SQL injection attacks using a machine-learning ensemble model. To create a trustworthy prediction model, the benefits of base learner algorithms—such as logistic regression, random forest, and decision trees—were combined with a cynosure on the stacking ensemble technique. To deal with the dataset's unequal nature, the ensemble model is trained and validated using a stratified approach. Performance measures like as F1-score, recall, accuracy, and precision are used to evaluate the model's effectiveness. With a 95% accuracy rate, the Stacking Ensemble model performs better than individual classifiers. A user-friendly web application was also developed that enables users to input SQL queries and obtain real-time predictions regarding the benignity or maliciousness of the queries. Users can interact with the model and see its performance in real time because to this interface's user-friendly platform. The ensemble model outperforms individual classifiers, according to first results, suggesting that it might be used practically to strengthen online application security against SQL injection threats.