To obtain access to full text of journal and articles you must register!
- Article name
- Hybrid method for identifying information security threats based on graph neural networks
- Authors
- Prudnikov S. I., , prudnikogroup@gmail.com, St. Petersburg Federal Research Center of the Russian Academy of Sciences, St. Petersburg, Russia
- Keywords
- information security / threat detection / graph neural network / transformer / event correlation / explainable artificial intelligence
- Year
- 2026 Issue 1 Pages 34 - 39
- Code EDN
- UCMVYB
- Code DOI
- 10.52190/2073-2600_2026_1_34
- Abstract
- This article presents an original hybrid method for identifying information security threats during automated processing. This method is based on graph neural networks, transformer models, and automatic security event correlation systems. The method implements pipeline processing of heterogeneous data with a closed feedback loop that enables adaptation to evolving threats. Key features of the method include: analysis of structural dependencies between system entities, semantic analysis of text logs using transformers, and complex event correlation with automated response and continuous learning based on explainable artificial intelligence.
- Text
- BUY for read the full text of article
- Buy
- 500.00 rub
