Automated Vulnerability Detection Using Deep Learning Technique

TL;DR

This paper presents a deep learning approach using CodeBERT and LSTM to improve the accuracy and scalability of vulnerability detection in Python code, specifically for SQL injection flaws.

Contribution

It introduces a novel deep learning framework combining CodeBERT and LSTM for more effective vulnerability detection compared to traditional static analysis tools.

Findings

Outperforms existing SAST tools in precision, recall, and F1-score.

Demonstrates scalability across multiple programming languages.

Shows significant improvement in detecting SQL injection vulnerabilities.

Abstract

Our work explores the utilization of deep learning, specifically leveraging the CodeBERT model, to enhance code security testing for Python applications by detecting SQL injection vulnerabilities. Unlike traditional security testing methods that may be slow and error-prone, our approach transforms source code into vector representations and trains a Long Short-Term Memory (LSTM) model to identify vulnerable patterns. When compared with existing static application security testing (SAST) tools, our model displays superior performance, achieving higher precision, recall, and F1-score. The study demonstrates that deep learning techniques, particularly with CodeBERT's advanced contextual understanding, can significantly improve vulnerability detection, presenting a scalable methodology applicable to various programming languages and vulnerability types.