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
| CREATOR | Saad Ahmed Ali Kalafy, Saied Pashazadeh, Pedram Salehpour |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 92 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |