Dynamic graph neural network-based framework to increase detection accuracy in SDN under DDOS

Saad Ahmed Ali Kalafy, Saied Pashazadeh, Pedram Salehpour · 2025

Read Dynamic graph neural network-based framework to increase detection accuracy in SDN under DDOS by Saad Ahmed Ali Kalafy, Saied Pashazadeh, Pedram Salehpour (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12816605.txt.

Description

Software-defined networks hand control to one programmable brain, which makes that brain a prime target for flood attacks. Saad Ahmed Ali Kalafy, Saied Pashazadeh, and Pedram Salehpour build a guard in a 2025 paper. Their guard, GCTNetwork, is a dynamic graph neural network that watches the network as a living graph rather than a pile of logs.

Its layers read node and edge features together, an edge-aware memory tracks how traffic evolves, and an attention layer spotlights the busiest communication paths. On a standard SDN dataset the system reached about ninety-four percent accuracy with a low false alarm index of 0.06, beating three advanced rival models. Training stayed stable, and the authors argue the design suits real-time defense where attack patterns keep shifting.

Catalog record

CREATORSaad Ahmed Ali Kalafy, Saied Pashazadeh, Pedram Salehpour
YEAR2025
COLLECTIONPAPERS
FORMATTXT
FILE SIZE92 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC12816605

Browse the full library · About the Tower of Babel