VULSOLVER: Vulnerability Detection via LLM-Driven Constraint Solving
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| 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 |