Metraipolis › archive › dc_cc699b39a4d3

GRAML: Graph-Grounded Reasoning and Multi-Task Learning for LLM-Based Software Vulnerability Detection — arXiv:2610.09605

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.09605
License (as archived)
CC0-1.0
Archived
2026-10-08T12:37:44.685Z
SHA-256 of the archived text
1f78a302d29b7d64e3d274ee68587f97b4eebc640ac812094e0d7e5e124a2a01
Stable URL of this page
https://metraipolis.com/documento/dc_cc699b39a4d3

How to cite

GRAML: Graph-Grounded Reasoning and Multi-Task Learning for LLM-Based Software Vulnerability Detection — arXiv:2610.09605 — arXiv (en), https://arxiv.org/abs/2610.09605 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cc699b39a4d3 (Metraipolis archive dc_cc699b39a4d3, sha256 1f78a302d29b7d64e3d274ee68587f97b4eebc640ac812094e0d7e5e124a2a01)
BibTeX
@misc{dccc699b39a4d3,
  title = {GRAML: Graph-Grounded Reasoning and Multi-Task Learning for LLM-Based Software Vulnerability Detection — arXiv:2610.09605},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.09605},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cc699b39a4d3; sha256 1f78a302d29b7d64e3d274ee68587f97b4eebc640ac812094e0d7e5e124a2a01},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09605. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large Language Models (LLMs) have been widely applied to software vulnerability detection. However, their performance is often limited by insufficient use of control-flow and data-flow information. In this paper, we propose GRAML, a framework that combines graph evidence, vulnerability description generation, and multi-task training. GRAML first performs static analysis on C/C++ programs to extract critical source lines and typed line relations as structural evidence. It then uses this evidence to guide GPT-5 through the Tree-of-Thought-guided Vulnerability Reasoning (ToT-VR) process and generate vulnerability descriptions. These descriptions are further combined with Detection, Localization, and Assessment samples to build a unified four-task training dataset. We evaluate GRAML on an in-distribution (ID) test set and six out-of-distribution (OOD) datasets. The results show that GRAML achieves average F1 scores ranging from 66.67% to 68.70%, outperforming state-of-the-art baselines by up to 30.92%. Ablation experiments further show that ToT-VR and graph-guided vulnerability descriptions improve detection performance compared with standard Chain-of-Thought (CoT) reasoning and raw Code Property Graph (CPG) serializations. These findings provide practical guidance for building more reliable and secure software engineering systems with large language models.

Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.SE, nuovi lavori del giorno).
Categorie arXiv: Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2610.09605 — 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 2026-10-08T12:14:30.243Z dalla pagina https://arxiv.org/list/cs.SE/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).