Neuro-symbolic Static Analysis with LLM-generated Vulnerability Patterns

[2504.16057] Neuro-symbolic Static Analysis with LLM-generated Vulnerability Patterns Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Cryptography and Security arXiv:2504.16057 (cs) [Submitted on 22 Apr 2025 ( v1 ), last revised 14 Apr 2026 (this version, v5)] Title: Neuro-symbolic Static Analysis with LLM-generated Vulnerability Patterns Authors: Penghui Li , Songchen Yao , Josef Sarfati Korich , Changhua Luo , Jianjia Yu , Yinzhi Cao , Junfeng Yang View a PDF of the paper titled Neuro-symbolic Static Analysis with LLM-generated Vulnerability Patterns, by Penghui Li and 6 other authors View PDF HTML (experimental) Abstract: In this work, we present MoCQ, a neuro-symbolic static analysis framework that leverages large language models (LLMs) to automatically generate vulnerability detection patterns. This approach combines the precision and scalability of pattern-based static analysis with the semantic understanding and automation capabilities of LLMs. MoCQ extracts the domain-specific languages for expressing vulnerability patterns and employs an iterative refinement loop with trace-driven symbolic validation that provides precise feedback for pattern correction. We evaluated MoCQ on 12 vulnerability types across four languages (C/C++, Java, PHP, JavaScript). MoCQ achieves detection performance comparable to expert-developed patterns while requiring only hours of generation versus weeks of manual effort. Notably, MoCQ uncovered 46 new vulnerability patterns that security experts had missed and discovered 25 previously unknown vulnerabilities in real-world applications. MoCQ also outperforms prior approaches with stronger analysis capabilities and broader applicability. Subjects: Cryptography and Security (cs.CR) Cite as: arXiv:2504.16057 [cs.CR] (or arXiv:2504.16057v5 [cs.CR] for this version) https://doi.org/10.48550/arXiv.2504.16057 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Penghui Li [ view email ] [v1] Tue, 22 Apr 2025 17:33:53 UTC (435 KB) [v2] Wed, 23 Apr 2025 18:03:24 UTC (414 KB) [v3] Sat, 26 Jul 2025 18:33:39 UTC (234 KB) [v4] Sun, 12 Apr 2026 01:48:18 UTC (365 KB) [v5] Tue, 14 Apr 2026 01:05:28 UTC (345 KB) Full-text links: Access Paper: View a PDF of the paper titled Neuro-symbolic Static Analysis with LLM-generated Vulnerability Patterns, by Penghui Li and 6 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CR < prev | next > new | recent | 2025-04 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Stacking faults from a different angle – Overcoming the edge-on limit in high-resolution defect analysis / Nicolas Karpstein, Lukas Müller, Andreas Bezold, Michael J. Mills, Steffen Neumeier, Erdmann Spiecker#983076
• Using Semantic Distance to Estimate Uncertainty in LLM-Based Code Generation#175348
• PrefixGuard: Online Failure Warning and Trace-Grounded Diagnosis for LLM Agents#1117393
• Calibrating Criterion Revision in LLM Agents: Failure Modes and a Trace-Anchored Protocol#659285
• Calibrating Criterion Revision in LLM Agents: Failure Modes and a Trace-Anchored Protocol#657149