Cybersecurity Threat Intelligence using Graph Neural Networks: A Survey and Future Directions
International Journal on Science and Technology · 09.04.2026 · 17 (2)
DOI: 10.71097/ijsat.v17.i2.10673 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal on Science and Technology, online erschienen am 09.04.2026. Verfasst von Ronak Goyal und 1 weiteren Autor:innen.
Abstract (Originalsprache)
This study explores the impact of Graph Neural Network (GNN) usage and Graph Feature Scores (GFS) on Threat Detection Accuracy (TDA) within cybersecurity systems. Using a structured questionnaire based on a 5-point Likert scale, data were collected from 242 cybersecurity professionals in New York. The analysis, conducted using R Studio, employed multiple regression techniques to assess the influence of GNN-based tools and graph feature integration on improving detection capabilities. The findings reveal a significant and positive relationship between both GNN Use and GFS with TDA, indicating that graph-based AI models can substantially enhance cybersecurity performance. The study contributes to the growing literature on AI-driven cybersecurity frameworks and highlights the practical relevance of GNNs in real-world threat intelligence. Future research can expand the model’s application to other sectors and geographies to validate scalability and adaptability.
Zitieren
APA
Goyal, R., & -, M. A. S. (2026). Cybersecurity Threat Intelligence using Graph Neural Networks: A Survey and Future Directions. International Journal on Science and Technology, 17(2). https://doi.org/10.71097/ijsat.v17.i2.10673
Vancouver
Goyal R, - MAS. Cybersecurity Threat Intelligence using Graph Neural Networks: A Survey and Future Directions. International Journal on Science and Technology. 2026;17(2). doi:10.71097/ijsat.v17.i2.10673
BibTeX
@article{Goyal2026,
author = {Goyal, Ronak and -, Mrs. Ashwini Somani},
title = {Cybersecurity Threat Intelligence using Graph Neural Networks: A Survey and Future Directions},
journal = {International Journal on Science and Technology},
year = {2026},
volume = {17},
number = {2},
doi = {10.71097/ijsat.v17.i2.10673}
}
EUVIMED