Metraipolis › archive › dc_bbbd955d1290

VulValidate: Auditing Function-Level Vulnerability Labels with Executable Evidence — arXiv:2610.05103

Source
arXiv
Original
https://arxiv.org/abs/2610.05103
License (as archived)
CC0-1.0
Archived
2026-10-06T05:26:41.261Z
SHA-256 of the archived text
24402725a20d8f4ccd446c371e8a53ccbd2df5ee974ddd19be10d00b9436dba5
Stable URL of this page
https://metraipolis.com/documento/dc_bbbd955d1290

How to cite

VulValidate: Auditing Function-Level Vulnerability Labels with Executable Evidence — arXiv:2610.05103 — arXiv, https://arxiv.org/abs/2610.05103 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bbbd955d1290 (Metraipolis archive dc_bbbd955d1290, sha256 24402725a20d8f4ccd446c371e8a53ccbd2df5ee974ddd19be10d00b9436dba5)
BibTeX
@misc{dcbbbd955d1290,
  title = {VulValidate: Auditing Function-Level Vulnerability Labels with Executable Evidence — arXiv:2610.05103},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.05103},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bbbd955d1290; sha256 24402725a20d8f4ccd446c371e8a53ccbd2df5ee974ddd19be10d00b9436dba5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.05103. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Reliable learning-based vulnerability detection requires high-quality labels, yet datasets built from vulnerability-fixing commits may label functions as vulnerable simply because they were changed by a security patch. We present VulValidate, a framework that uses LLM agents to coordinate dynamic analysis tools and construct vulnerability-triggering experiments from runtime feedback. Given a labeled function and its fixing patch, VulValidate reconstructs vulnerable and fixed revisions, selects suitable tools and execution paths, refines triggering inputs, and compares runtime behavior to assess function-level attribution. We audit all 35,849 instances originally labeled vulnerable in BigVul, PrimeVul, and DiverseVul. We confirm 20,510 (57.2%), correct 6,819 labels (19.0%), leave 7,981 attacked but undecided (22.3%), and cannot successfully measure 539 (1.5%). After conflict resolution and byte-exact deduplication, the corrected release contains 15,890 distinct confirmed vulnerable function bodies. In a blinded review of 581 sampled decisions, expert consensus supports 90.0%--92.0% of confirmations and 92.6%--99.0% of label corrections. With model parameters fixed, corrected evaluation lowers F1 for all five tested detectors on both BigVul and DiverseVul; retraining with corrected labels improves F1 for four of five detectors on each dataset. We also release a reusable VulValidate skill, corrected datasets, and reproducible evidence for future vulnerability-detection research.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI); Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2610.05103 — 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 2026-10-06T05:24:05.969Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).