GADD: Game-Inspired Adversarial Distillation for Robust Graph Defense
Graph neural networks (GNNs) are highly effective on relational data, yet their performance degrades sharply when graph topology is poisoned before training. Existing defenses usually assume a fixed attack pattern and a fixed graph structure, which makes them brittle when the poisoned graph changes...
Gardado en:
| Principais autores: | , , , , , |
|---|---|
| Formato: | Artigo |
| Idioma: | Inglês |
| Publicado: |
MDPI AG
2026-05-01
|
| Series: | Information |
| Assuntos: | |
| Acceso en liña: | https://www.mdpi.com/2078-2489/17/6/527 |
| Tags: |
Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!
|