GDDM is a diffusion-based purification method with a graph structure refiner and node feature regularizer that defends against multiple adversarial attack types on graphs.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Graph Defense Diffusion Model
GDDM is a diffusion-based purification method with a graph structure refiner and node feature regularizer that defends against multiple adversarial attack types on graphs.