Saved in:
Bibliographic Details
Main Authors: Sheng, Ze, Wu, Fenghua, Zuo, Xiangwu, Li, Chao, Qiao, Yuxin, Hang, Lei
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2411.06493
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916479803326464
author Sheng, Ze
Wu, Fenghua
Zuo, Xiangwu
Li, Chao
Qiao, Yuxin
Hang, Lei
author_facet Sheng, Ze
Wu, Fenghua
Zuo, Xiangwu
Li, Chao
Qiao, Yuxin
Hang, Lei
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2411_06493
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LProtector: An LLM-driven Vulnerability Detection System
Sheng, Ze
Wu, Fenghua
Zuo, Xiangwu
Li, Chao
Qiao, Yuxin
Hang, Lei
Cryptography and Security
Artificial Intelligence
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.
title LProtector: An LLM-driven Vulnerability Detection System
topic Cryptography and Security
Artificial Intelligence
url https://arxiv.org/abs/2411.06493