Metraipolis › archive › dc_e83e07ccb22e
Neuro-Symbolic Proof-of-Vulnerability Generation with Open-Weight Models — arXiv:2608.04217
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.04217
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T11:36:32.008Z
- SHA-256 of the archived text
dd5ae124074c4e80c8cd7ced64fa3bda330422f9686263c8e05da588ee444249- Stable URL of this page
https://metraipolis.com/documento/dc_e83e07ccb22e
How to cite
Neuro-Symbolic Proof-of-Vulnerability Generation with Open-Weight Models — arXiv:2608.04217 — arXiv (en), https://arxiv.org/abs/2608.04217 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e83e07ccb22e (Metraipolis archive dc_e83e07ccb22e, sha256 dd5ae124074c4e80c8cd7ced64fa3bda330422f9686263c8e05da588ee444249)
BibTeX
@misc{dce83e07ccb22e,
title = {Neuro-Symbolic Proof-of-Vulnerability Generation with Open-Weight Models — arXiv:2608.04217},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.04217},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e83e07ccb22e; sha256 dd5ae124074c4e80c8cd7ced64fa3bda330422f9686263c8e05da588ee444249},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04217. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Software vulnerabilities are persistent, but validating them remains difficult: a Proof-of-Vulnerability (PoV) requires a concrete input that triggers the vulnerable behavior, yet public triggering inputs are often unavailable for disclosed vulnerabilities. Existing techniques make different tradeoffs in effectiveness, scalability, cost, and controllability, leaving room for complementary designs. To complement them, we present POVGEN, a low-cost neuro-symbolic framework that makes PoV generation cost-effective via semantic focusing and LLM-guided constraint reasoning using open-weight models. POVGEN first localizes vulnerability-relevant regions (utilizing patch information if available), then performs path-sensitive reachability analysis, and finally generates PoVs by extracting and solving constraints with LLM-guided reasoning backed by an SMT solver. POVGEN successfully generates PoVs for 78.98% of vulnerabilities in a recent benchmark, outperforming fuzzing (up to 50.20%) and symbolic execution (2.45%). On 250 real-world CVEs without public PoVs, it generates valid PoVs for 74.80% of cases and reproduces 65.1% when without patch information. 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). Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-06 in cs.SE). Categorie arXiv: Software Engineering (cs.SE). Pagina del lavoro: https://arxiv.org/abs/2608.04217 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-31T11:25:52.389Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).