Design and evaluation of an optimized genetic algorithm model for SQL injection intrusion detection and prevention

SQL Injection (SQLi) attacks continue to represent a major threat to the security of database-driven web applications, despite the availability of numerous detection and prevention techniques. Conventional approaches such as static rule-based filtering, signature-based detection, and traditional machine learning models often lack adaptability, suffer from high false-positive rates, and demonstrate limited effectiveness against evolving and zero-day attack patterns. To address these challenges, this research focuses on the design and evaluation of an optimized genetic algorithm model for SQL injection intrusion detection and prevention model. The proposed model formulates SQL injection detection as an optimization problem, where candidate detection rules are encoded as chromosomes derived from syntactic, semantic, and behavioral characteristics of SQL queries. Through evolutionary processes involving selection, crossover, and mutation, the genetic algorithm iteratively refines these rules to maximize detection accuracy while minimizing false positives. The adaptive nature of the GA enables the system to evolve in response to emerging attack vectors without extensive manual intervention or frequent retraining. Beyond detection, the model incorporates a real-time prevention mechanism that intercepts and neutralizes malicious queries before database execution, thereby strengthening overall system resilience. The effectiveness of the proposed framework is rigorously evaluated using benchmark datasets from real-world traffic traces, and simulated SQL injection scenarios. The designed specifically for web application intrusion detection use the dataset which includes SQL injection, XSS, buffer overflow. The expected contribution of this research is a robust, scalable, and self-optimizing intrusion detection and prevention model that advances the state of the art in SQL injection mitigation. By integrating evolutionary computation techniques into web application security, the study provides both theoretical insights and practical solutions for enhancing database security in modern computing environments.