EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Graph Neural Networks for Software Vulnerability Mining: A Review

Yuan He, Haikun Lv, Xing Li, Lulu Zeng, Lina Zhang, Dengqi Yang, Xiaowei Li

Information · 28.07.2026 · 17 (8) · 730

DOI: 10.3390/info17080730 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Information, online erschienen am 28.07.2026. Verfasst von Yuan He und 6 weiteren Autor:innen. Die Arbeit nennt 96 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Dali University, Yunnan Provincial Department of Education.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Software vulnerability mining is important for improving software reliability and security. Compared with sequence-based models, graph neural networks (GNNs) can explicitly model program structures such as syntax, control flow, data flow, call relations, and dependency paths, and have therefore been widely studied for vulnerability detection, localization, explanation, and repair. This paper presents a PRISMA-informed structured topical review of 87 studies and addresses five research questions concerning program graph representation, homogeneous and heterogeneous GNN architectures, Graph–LLM integration, evaluation reliability, and future research directions. The reviewed evidence shows that graph-based methods are most effective when vulnerability mechanisms can be faithfully represented through explicit structural relations. However, their reported performance remains strongly affected by duplicated samples, random function-level splits, noisy labels, incomplete repository context, graph-construction errors, and weak explanation protocols. Homogeneous GNNs provide efficient structural message passing but may mix different semantic relations, whereas heterogeneous GNNs preserve relation types more explicitly at the cost of greater graph-quality and computational requirements. Graph–LLM systems can improve semantic reasoning, repository-level analysis, explanation generation, and repair support, but their benefits should be evaluated together with memory consumption, inference latency, deployment complexity, and verification cost. This review further proposes minimum requirements for reliable vulnerability benchmarks and verifiable explanations, and develops a strategic agenda covering leakage-resistant datasets, uncertainty-aware graph construction, repository-level evaluation, cost-effective Graph–LLM collaboration, and graph-guided autonomous vulnerability repair.

Förderung

  • National Natural Science Foundation of China
  • Dali University
  • Yunnan Provincial Department of Education

Zitieren

APA

He, Y., Lv, H., Li, X., Zeng, L., Zhang, L., Yang, D., & Li, X. (2026). Graph Neural Networks for Software Vulnerability Mining: A Review. Information, 17(8), 730. https://doi.org/10.3390/info17080730

Vancouver

He Y, Lv H, Li X, Zeng L, Zhang L, Yang D, et al. Graph Neural Networks for Software Vulnerability Mining: A Review. Information. 2026;17(8):730. doi:10.3390/info17080730

BibTeX
@article{He2026,
  author = {He, Yuan and Lv, Haikun and Li, Xing and Zeng, Lulu and Zhang, Lina and Yang, Dengqi and Li, Xiaowei},
  title = {Graph Neural Networks for Software Vulnerability Mining: A Review},
  journal = {Information},
  year = {2026},
  volume = {17},
  number = {8},
  pages = {730},
  doi = {10.3390/info17080730}
}
Kostenlos starten →