SecureBERT-Fused R-GCN for Cyber Threat Intelligence Knowledge Graph Completion: Extending KGE-SymCL on MITRE ATT&CK
International Journal for Research in Applied Science and Engineering Technology · 30.11.2026 · 14 (11) · 562-573
DOI: 10.22214/ijraset.2026.85579 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal for Research in Applied Science and Engineering Technology, online erschienen am 30.11.2026. Verfasst von Nallapureddy Pranitha und 1 weiteren Autor:innen.
Abstract (Originalsprache)
Knowledge graph embedding (KGE) is widely used to complete cyber threat intelligence (CTI) graphs, yet most methods rely on graph structure alone and are validated on general-purpose benchmarks that differ sharply from security data. CTI graphs have a small relation vocabulary, and their entities carry much of their meaning in technical text. This study applies KGE-SymCL, a contrastive learning approach that considers the symmetry of relations, to a cyber threat intelligence (CTI) graph derived from MITRE ATT&CK Enterprise v19.1. The graph comprises 2,595 entities, 20,866 triples, and five distinct relation types. We propose an R-GCN encoder whose structural embeddings are merged with SecureBERT text embeddings through a learned gate. Fifteen KGE backbones are compared, with and without the SymCL term, under an identical protocol over three random seeds. SymCL improves the purely structural R-GCN (MRR 0.0904 to 0.0977) but adds little once SecureBERT fusion is present. The fused model reaches an MRR of 0.1102, a significant gain over plain R-GCN (p = 0.015), although CompGCN and SimKGC remain higher on Hit@1 and Hit@3. These results show that the benefit of contrastive alignment depends on what other signal the encoder already has. To support forensic use, we also add multi-hop path explanations, fusion-gate analysis and tamper-robustness tests that check how predictions behave when the graph is perturbed.
Zitieren
APA
Pranitha, N., & Rao, D. C. D. V. S. (2026). SecureBERT-Fused R-GCN for Cyber Threat Intelligence Knowledge Graph Completion: Extending KGE-SymCL on MITRE ATT&CK. International Journal for Research in Applied Science and Engineering Technology, 14(11), 562-573. https://doi.org/10.22214/ijraset.2026.85579
Vancouver
Pranitha N, Rao DCDVS. SecureBERT-Fused R-GCN for Cyber Threat Intelligence Knowledge Graph Completion: Extending KGE-SymCL on MITRE ATT&CK. International Journal for Research in Applied Science and Engineering Technology. 2026;14(11):562-573. doi:10.22214/ijraset.2026.85579
BibTeX
@article{Pranitha2026,
author = {Pranitha, Nallapureddy and Rao, Dr. Ch. D V Subba},
title = {SecureBERT-Fused R-GCN for Cyber Threat Intelligence Knowledge Graph Completion: Extending KGE-SymCL on MITRE ATT&CK},
journal = {International Journal for Research in Applied Science and Engineering Technology},
year = {2026},
volume = {14},
number = {11},
pages = {562--573},
doi = {10.22214/ijraset.2026.85579}
}
EUVIMED