Augmenting SQL Injection Attack Detection via Deep Convolutional Neural Network

Abstract Advancing the systematic methods or algorithms is necessary because SQL injection attacks can be hazardous for the security of databases and various web applications. SQL injection can be a destructive security risks which targets vulnerable web applications. There were many techniques which was previously developed which is also known as traditional methods or techniques. Those techniques used to generally rely on the signature-based methods which struggle to adjust into new attack patterns. Therefore, different new techniques were introduced with integration of machine learning. SQL injection attack detection with the blend of machine learning facilitates improvement in cybersecurity providing the scalable and the proficient defense mechanism against the developing cyber-attack. This research paper provides a potential technique to the danger of SQL injection which is based on Machine Learning i.e. Deep Convolutional Neural Network (DCNN). The proposed model was trained on the large datasets which includes genuine as well as malicious SQL queries for assuring its ability to adapt different types of evolving attacks. We have used embedding layers and tokenization techniques for demonstrating SQL queries as numerical input for the model. It is made up of many convolutional layers and fully linked layers which is able to illustrate the complex patterns and the complex correlation that can be observed in SQL queries. Our approach to detect a SQL injection attack utilizing a DCNN illustrates the remarkable accuracy, precision, recall as well as F1 score. Additionally, we also had a look at the significances of using deep learning techniques in real-world scenarios along with the existing web application and the framework.