article
Traditional security systems based on perimeter protection become ineffective when trying to prevent lateral attacks that occur after users gain access to systems. We present CogGAT as a new Cognitive Behavioral Intrusion Prevention System (IPS) that uses a Granular Zero-Trust Security Framework. The process of developing Graph Attention Networks (GATs) enables us to change their attention mechanisms into real-time Trust Scores. Our framework reached an accuracy of 0.95-0.96 and reduced DPI resource consumption by 47.3% based on testing with the complete BoT-IoT and ToN_IoT datasets. The discovery of Cognitive Dissonance shows our research at its most innovative point because this condition occurs when current device behavior conflicts with past device performance, which helps organizations handle risks before they arise in places with limited resources.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1109/iraset68627.2026.11538511
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
