Work

SQL Injection Attack Detection Based on Text-CNN

Year: 2024
Type: conference-paper
Abstract: In the digital age of the 21st century, with the widespread use of Web applications, SQL injection attacks have become one of the significant challenges in the field of information security. This study proposes a method for detecting SQL injection attacks based on an improved Text-CNN model. The method starts with the preprocessing of collected SQL injection attack data, followed by the use of the convolutional layers of the Text-CNN model to extract local features, and then combines the CAM attention mechanism to achieve the task of SQL injection detection. The introduction of the CAM attention mechanism aims to merge the information from max pooling and average pooling to reduce information loss and enhance the global representation capability of the model. Experimental results show that the proposed method has improved in terms of accuracy, precision, recall rate, and F1 score, with values of 92.40%, 92.45%, 92.29%, and 0.9237, respectively. Given that traditional Text-CNN, Text-RNN, and CNN algorithms can perform well in recognizing SQL injection attacks, this provides help for subsequent applications in network security protection.
Language: English
Open Access status: bronze
OpenAlex ID: W4400268391
FWCI: 0.318
Cites: 7
Cited by: 2
Related to: 10