Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{186696,
        author = {Akshay Hole and Abhale B.A. and Pranav Bankar and Shraddha Ghaytadkar and Diya Jejurkar and Mr.Pathare G},
        title = {The Rise of Relational AI: A Comprehensive Survey of Graph Neural Networks in Modern Cybersecurity Defenses},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {6},
        pages = {2434-2442},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=186696},
        abstract = {This comprehensive survey examines and consolidates research on the utilization of Graph Neural Networks (GNNs) within the cybersecurity domain. The study traces the progression from conventional feature-extraction-based intrusion detection methodologies to contemporary structure-cognizant defensive frameworks that exploit the fundamental relational characteristics inherent in cybersecurity data. The research systematically investigates core GNN architectures, sophisticated models designed for temporal and heterogeneous datasets, and their deployment in essential security applications including lateral movement identification and premptive threat reconnaissance. Particular emphasis is accorded to the necessity of Explainable Artificial Intelligence (XAI) methodologies to reconcile the complexity of model outputs with practical security decision-making processes. The authors conduct a rigorous examination of enduring obstacles within this field, encompassing computational scalability, data integrity, real-time analytical capabilities, and resilience against adversarial attacks. Through the integration of contemporary research developments, this survey elucidates prevailing scholarly trajectories, delineates significant lacunae in existing literature, and delineates prospective avenues for advancing artificial intelligence applications in cybersecurity research and practice.},
        keywords = {Graph Neural Networks, Security Operation Centre, Proactive systems, Cyber Security, Temporal Heterogeneous Graph Neural   Network (THGNN), Explainable AI (XAI), survey},
        month = {November},
        }