Structured query language injection detection with natural language processing techniques optimized by metaheuristics

Abstract

This research focuses on the detection of Structured Query Language (SQL) injection intrusion detection. This problem has gained significance due to the widespread use of SQL in different systems, as well as for the numerous versions of attacks that are performable by using this technique. This work aims to propose a robust solution for the detection of such attacks by applying artificial intelligence (AI). The data is preprocessed by a Bidirectional Encoder Representations from Transformers (BERT), while the predictions are made by the Extreme Gradient Boosting (XGBoost) algorithm. The XGBoost is a powerful predictor if optimized correctly. Hyperparameters are optimized by an improved version of the Crayfish Optimization Algorithm (COA) hybridized with the Genetic Algorithm (GA). The proposed solution is tested against highperforming metaheuristics in which it achieved favorable performance.