2000 character limit reached
QLPro: Automated Code Vulnerability Discovery via LLM and Static Code Analysis Integration (2506.23644v1)
Published 30 Jun 2025 in cs.SE, cs.AI, and cs.CR
Abstract: 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.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.