EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

GRAL: A GNN-RAG-LLM Framework for Intelligent Cybersecurity Alert Correlation and Analysis

Deng Zhang, Juan Wang, Hanjun Gao, Yuyao Feng, Chengliangyi Xia, Daijie Sun, Gang Shen

Symmetry · 07.08.2026 · 18 (8) · 1334

DOI: 10.3390/sym18081334 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Symmetry, online erschienen am 07.08.2026. Verfasst von Deng Zhang und 6 weiteren Autor:innen. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In critical infrastructure environments, cybersecurity situation-awareness platforms generate large volumes of alerts, including substantial numbers of false positives, placing a considerable burden on security analysts. At present, alert correlation methods mainly rely on rule-based matching or statistical clustering, and large language models often lack the domain-specific threat intelligence required for reliable security analysis. This paper proposes GRAL, which is an AI-driven framework that combines graph neural networks (GNN) for cross-asset temporal alert correlation, retrieval-augmented generation (RAG) for dynamic threat intelligence enrichment, and large language models (LLM) for semantic reasoning and verdict generation. A temporal heterogeneous graph attention network constructs alert-relation graphs within a 72 h sliding window, and temporal decay and multi-relational dependencies are captured. Powered by bge-m3 embeddings and a dense vector index, the RAG module retrieves the most relevant threat intelligence entries above a cosine similarity threshold of 0.75. A domain-specific dataset of 1000 annotated security alerts from a nuclear power operational environment was built, and Cohen’s Kappa reached 0.87. The experiments show that GRAL achieves a macro-averaged precision of 87.0%, a macro-averaged recall of 97.0%, and a binary false-positive rate of 9.1%, together with 92.5% alert compression. Generalisation capability is confirmed by cross-dataset evaluation on CICIDS2017 (93.0% accuracy and 92.5% F1-score) and UNSW-NB15 (89.4% accuracy and 89.8% F1-score).

Zitieren

APA

Zhang, D., Wang, J., Gao, H., Feng, Y., Xia, C., Sun, D., & Shen, G. (2026). GRAL: A GNN-RAG-LLM Framework for Intelligent Cybersecurity Alert Correlation and Analysis. Symmetry, 18(8), 1334. https://doi.org/10.3390/sym18081334

Vancouver

Zhang D, Wang J, Gao H, Feng Y, Xia C, Sun D, et al. GRAL: A GNN-RAG-LLM Framework for Intelligent Cybersecurity Alert Correlation and Analysis. Symmetry. 2026;18(8):1334. doi:10.3390/sym18081334

BibTeX
@article{Zhang2026,
  author = {Zhang, Deng and Wang, Juan and Gao, Hanjun and Feng, Yuyao and Xia, Chengliangyi and Sun, Daijie and Shen, Gang},
  title = {GRAL: A GNN-RAG-LLM Framework for Intelligent Cybersecurity Alert Correlation and Analysis},
  journal = {Symmetry},
  year = {2026},
  volume = {18},
  number = {8},
  pages = {1334},
  doi = {10.3390/sym18081334}
}
Kostenlos starten →