Neuro-Symbolic Proof-of-Vulnerability Generation with Open-Weight Models
Source
Yu Nong, Haipeng Cai
Author
Yu Nong, Haipeng Cai
Date
Terms in this piece · Glossary
open weights — A model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.
LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.
Why it matters
It shows LLMA large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.Full definition →-guided constraint reasoning decisively beating fuzzing at vulnerability validation, and that a locally-run open weightsA model whose trained parameters are published for anyone to download and run — unlike API-only models you can access but never possess.Full definition → model is enough to do it — no frontier API bill required.
Key quotes
“POVGEN successfully generates PoVs for 78.98% of vulnerabilities in a recent benchmark, outperforming fuzzing (up to 50.20%) and symbolic execution (2.45%).”
“The fine-tuned open-weight models match frontier commercial LLMs on key sub-tasks (i.e., the core constraint-reasoning steps) while running locally at no per-sample API cost.”
“Applying the generated PoVs revealed six flawed patches in disclosed CVEs (all subsequently fixed) and five previously unreported vulnerabilities (of which four have been confirmed and fixed by the developers).”
articleGraph Is the Verifier: Agentic Reinforcement Learning for Interprocedural Vulnerability DetectionYikun Li, Ting Zhang, Jiakun Liu, Jinfeng Jiang, Yuheng Yieh, Yixin Yang, Wen Bin Leow, Yide Yin, Yintong Huo, Eng Lieh Ouh, Lwin Khin Shar, David Lo
articleAutomated Vulnerability Injection in Smart Contracts Using Large Language ModelsLuca Migliaccio, Roberto Natella, Naghmeh Ivaki, Nuno Laranjeiro, Marco Vieira
articleLLMVul: A Vulnerability-Labeled Dataset of LLM-Generated C/C++ Functions from Real Production RepositoriesMohammad Farhad, Shuvalaxmi Dass