Intelligent Detection of Injection Attacks via SQL Based on Supervised Machine Learning Models for Enhancing Web Security

Abstract

The most prevalent technique behind security data breaches exists through SQL Injection Attacks. Organizations and individuals suffer from sensitive information exposure and unauthorized entry when attackers take advantage of SQL injection (SQLi) attack vulnerability's severe risks. Static and heuristic defense methods remain conventional detection tools for previous SQL injection attacks study's foundation is a detection system developed using the Gated Recurrent Unit (GRU) network, which attempts to efficiently identify SQL Injection attacks (SQLIAs). The suggested Gated Recurrent Unit model was trained using an 80:20 train-test split, and the results showed that SQL injection attacks could be accurately identified with a precision rate of 97%, an accuracy rate of 96.65%, a recall rate of 92.5%, and an F1-score of 94%. The experimental results, together with their corresponding confusion matrix analysis and learning curves, demonstrate resilience and outstanding generalization ability. The GRU model outperforms conventional machine learning (ML) models, including K-Nearest Neighbor's (KNN), and Support Vector Machine (SVM), in terms of identifying sequential patterns in SQL query data. Recurrent neural architecture proves effective in the detection of SQLi attacks through its ability to provide secure protection for contemporary web applications.

Keywords: Web Application Security, Cyberattacks, SQL Injection Attacks (SQLIA), Machine Learning (ML), SQL Injection Dataset