SQL injection attack sample generation based on IE-GAN

The relentless advancement of Generative Adversarial Network (GAN) technology has stimulated research interest in exploiting its unique properties within the realm of network security. In conjunction with the maturity and growth of artificial intelligence, employing AI technology for SQL injection detection has evolved into an unalterable trend. This study introduces the application of an Improved Evolutionary Generative Adversarial Network (IE-GAN) for the synthesis of SQL injection attacks, thereby facilitating the generation of realistic SQL injection attack examples. Given the considerable threat posed by SQL injection attacks to the security of web applications, the demand for robust and efficient detection mechanisms has escalated significantly. Earlier research has made considerable progress in incorporating GANs in the field of cybersecurity.Our study builds upon these achievements, utilizing a comprehensive dataset that includes both benign and malicious SQL queries. To ensure the efficiency of model training, these data are subjected to intricate preprocessing and vectorization processes, which are discussed in the paper in detail.