VULSOLVER: Vulnerability Detection via LLM-Driven Constraint Solving

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Xiang, Su, Yueci, Liu, Jiahao, Lin, Zhiwei, Hou, Yuebing, Gao, Peiming, Zhang, Yuanchao
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914169694978048
author Li, Xiang
Su, Yueci
Liu, Jiahao
Lin, Zhiwei
Hou, Yuebing
Gao, Peiming
Zhang, Yuanchao
author_facet Li, Xiang
Su, Yueci
Liu, Jiahao
Lin, Zhiwei
Hou, Yuebing
Gao, Peiming
Zhang, Yuanchao
contents Traditional vulnerability detection methods rely heavily on predefined rule matching, which often fails to capture vulnerabilities accurately. With the rise of large language models (LLMs), leveraging their ability to understand code semantics has emerged as a promising direction for achieving more accurate and efficient vulnerability detection. However, current LLM-based approaches face significant challenges: instability in model outputs, degraded performance with long context, and hallucination. As a result, many existing solutions either use LLMs merely to enrich predefined rule sets, thereby keeping the detection process fundamentally rule-based, or over-rely on them, leading to poor robustness. To address these challenges, we propose a constraint-solving approach powered by LLMs named VULSOLVER. By modeling vulnerability detection as a constraint-solving problem, and by integrating static application security testing (SAST) with the semantic reasoning capabilities of LLMs, our method enables the LLM to act like a professional human security expert. We assess VULSOLVER on the OWASP Benchmark (1,023 labeled samples), achieving 97.85% accuracy, 97.97% F1-score, and 100% recall. Applied to widely-used open-source projects, VULSOLVER identified 15 previously unknown high-severity vulnerabilities (CVSS 7.5-9.8), demonstrating its effectiveness in real-world security analysis.
format Preprint
id arxiv_https___arxiv_org_abs_2509_00882
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VULSOLVER: Vulnerability Detection via LLM-Driven Constraint Solving
Li, Xiang
Su, Yueci
Liu, Jiahao
Lin, Zhiwei
Hou, Yuebing
Gao, Peiming
Zhang, Yuanchao
Cryptography and Security
Traditional vulnerability detection methods rely heavily on predefined rule matching, which often fails to capture vulnerabilities accurately. With the rise of large language models (LLMs), leveraging their ability to understand code semantics has emerged as a promising direction for achieving more accurate and efficient vulnerability detection. However, current LLM-based approaches face significant challenges: instability in model outputs, degraded performance with long context, and hallucination. As a result, many existing solutions either use LLMs merely to enrich predefined rule sets, thereby keeping the detection process fundamentally rule-based, or over-rely on them, leading to poor robustness. To address these challenges, we propose a constraint-solving approach powered by LLMs named VULSOLVER. By modeling vulnerability detection as a constraint-solving problem, and by integrating static application security testing (SAST) with the semantic reasoning capabilities of LLMs, our method enables the LLM to act like a professional human security expert. We assess VULSOLVER on the OWASP Benchmark (1,023 labeled samples), achieving 97.85% accuracy, 97.97% F1-score, and 100% recall. Applied to widely-used open-source projects, VULSOLVER identified 15 previously unknown high-severity vulnerabilities (CVSS 7.5-9.8), demonstrating its effectiveness in real-world security analysis.
title VULSOLVER: Vulnerability Detection via LLM-Driven Constraint Solving
topic Cryptography and Security
url https://arxiv.org/abs/2509.00882