SQL_Injection_Detection_Dataset

SQL Injection (SQLi) continues to be a prevalent and critical security vulnerability, posing a significant threat to web applications and database integrity. The development of effective and robust detection systems for SQLi attacks is a major area of research in cybersecurity. Machine learning and deep learning models have shown great promise in this domain; however, their performance is heavily reliant on the quality and diversity of the training data.This paper presents a comprehensive dataset for SQL injection detection, containing a total of 244,068 SQL queries. The dataset is meticulously curated and labeled, comprising 136,740 malicious SQL injection queries and 107,328 benign SQL queries. The collection encompasses a wide variety of SQLi attack patterns, ranging from simple tautologies to more complex and obfuscated injection techniques, alongside a vast collection of legitimate SQL queries.The primary purpose of this dataset is to serve as a valuable resource for the research community. It can be effectively utilized for training, testing, and benchmarking machine learning and deep learning-based intrusion detection systems. The balanced and extensive nature of the dataset makes it suitable for developing and evaluating models with high accuracy and low false-positive rates. By making this dataset publicly available, we aim to facilitate advancements in the field of automated SQL injection detection and contribute to the development of more secure web applications.