GLG reconstructs node features and graph structure from GNN gradients in federated learning, achieving near-perfect recovery for GraphSAGE and high accuracy for GCN under per-node gradient threat models.
Brendan McMahan, Ilya Mironov, Kunal Talwar, and Li Zhang
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Gradient Inversion Attack on Graph Neural Networks
GLG reconstructs node features and graph structure from GNN gradients in federated learning, achieving near-perfect recovery for GraphSAGE and high accuracy for GCN under per-node gradient threat models.