QLPro: Automated Code Vulnerability Discovery via LLM and Static Code Analysis Integration

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hu, Junze, Jin, Xiangyu, Zeng, Yizhe, Liu, Yuling, Li, Yunpeng, Du, Dan, Xie, Kaiyu, Zhu, Hongsong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908456608333824
author Hu, Junze
Jin, Xiangyu
Zeng, Yizhe
Liu, Yuling
Li, Yunpeng
Du, Dan
Xie, Kaiyu
Zhu, Hongsong
author_facet Hu, Junze
Jin, Xiangyu
Zeng, Yizhe
Liu, Yuling
Li, Yunpeng
Du, Dan
Xie, Kaiyu
Zhu, Hongsong
contents We introduce QLPro, a vulnerability detection framework that systematically integrates LLMs and static analysis tools to enable comprehensive vulnerability detection across entire open-source projects.We constructed a new dataset, JavaTest, comprising 10 open-source projects from GitHub with 62 confirmed vulnerabilities. CodeQL, a state-of-the-art static analysis tool, detected only 24 of these vulnerabilities while QLPro detected 41. Furthermore, QLPro discovered 6 previously unknown vulnerabilities, 2 of which have been confirmed as 0-days.
format Preprint
id arxiv_https___arxiv_org_abs_2506_23644
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle QLPro: Automated Code Vulnerability Discovery via LLM and Static Code Analysis Integration
Hu, Junze
Jin, Xiangyu
Zeng, Yizhe
Liu, Yuling
Li, Yunpeng
Du, Dan
Xie, Kaiyu
Zhu, Hongsong
Software Engineering
Artificial Intelligence
Cryptography and Security
We introduce QLPro, a vulnerability detection framework that systematically integrates LLMs and static analysis tools to enable comprehensive vulnerability detection across entire open-source projects.We constructed a new dataset, JavaTest, comprising 10 open-source projects from GitHub with 62 confirmed vulnerabilities. CodeQL, a state-of-the-art static analysis tool, detected only 24 of these vulnerabilities while QLPro detected 41. Furthermore, QLPro discovered 6 previously unknown vulnerabilities, 2 of which have been confirmed as 0-days.
title QLPro: Automated Code Vulnerability Discovery via LLM and Static Code Analysis Integration
topic Software Engineering
Artificial Intelligence
Cryptography and Security
url https://arxiv.org/abs/2506.23644