Pith. sign in

Hence, the performance may improve if attack techniques for batch data are also incorporated

have been proposed to reconstruct image data from large batches, here we tested the performance of the attackers by simply optimizing with respect to the dummy input batch · 2025

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it
browse 1 citing papers

fields

cs.LG 1

years

2024 1

verdicts

CONDITIONAL 1

representative citing papers

Gradient Inversion Attack on Graph Neural Networks

cs.LG · 2024-11-29 · conditional · novelty 5.0

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.

citing papers explorer

Showing 1 of 1 citing paper.

  • Gradient Inversion Attack on Graph Neural Networks cs.LG · 2024-11-29 · conditional · none · ref 18

    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.