LProtector: An LLM-driven Vulnerability Detection System
This addresses the challenge of effective vulnerability detection for software developers as complexity grows, but it is incremental as it builds on existing LLM and RAG methods.
The paper tackles the problem of automated vulnerability detection in C/C++ codebases by introducing LProtector, a system that uses GPT-4o and Retrieval-Augmented Generation (RAG), and it shows that LProtector outperforms two state-of-the-art baselines in F1 score on the Big-Vul dataset.
This paper presents LProtector, an automated vulnerability detection system for C/C++ codebases driven by the large language model (LLM) GPT-4o and Retrieval-Augmented Generation (RAG). As software complexity grows, traditional methods face challenges in detecting vulnerabilities effectively. LProtector leverages GPT-4o's powerful code comprehension and generation capabilities to perform binary classification and identify vulnerabilities within target codebases. We conducted experiments on the Big-Vul dataset, showing that LProtector outperforms two state-of-the-art baselines in terms of F1 score, demonstrating the potential of integrating LLMs with vulnerability detection.