Development of an SQL injection detection and prevention model using genetic algorithm

Abstract

SQL injection is a common and dangerous attack vector in web applications that allows attackers to execute malicious SQL queries to gain unauthorized access to the database. We aim to develop a more adaptive and resilient system that can dynamically evolve and adapt to new attack patterns. SQL injection detection and prevention has the potential to significantly improve the security of web applications and provide better protection against SQL injection attacks. Intrusion detection and prevention systems (IDPS) play a critical role in safeguarding computer networks from malicious activities and security breaches. Traditional IDPS solutions often struggle to adapt to evolving threats and exhibit limitations in accurately detecting and preventing sophisticated attacks. This approach is for enhancing IDPS capabilities through the integration of a hybrid genetic algorithm (HGA). By combining the evolutionary search capabilities of genetic algorithms with the domain-specific knowledge and rules of intrusion detection systems, the proposed HGA offers a robust framework for improving detection accuracy and reducing false positives. The hybridization process involves incorporating genetic operators, such as crossover and mutation, into the rule-based detection mechanisms of IDPS. Additionally, the HGA dynamically adjusts detection thresholds and parameters based on real-time network traffic analysis, enabling adaptive and proactive defense mechanisms against emerging threats.