Pith. sign in

Title resolution pending

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

1 Pith paper citing it

fields

cs.LG 1

years

2025 1

verdicts

REJECT 1

representative citing papers

Unifying Adversarial Perturbation for Graph Neural Networks

cs.LG · 2025-08-30 · reject · novelty 3.0

Adding perturbations directly to every hidden embedding of a GNN is claimed to subsume existing feature-, edge-, and weight-perturbation defenses, but the claim rests on simplifications that the experiments do not actually test.

citing papers explorer

Showing 1 of 1 citing paper.

  • Unifying Adversarial Perturbation for Graph Neural Networks cs.LG · 2025-08-30 · reject · none · ref 40

    Adding perturbations directly to every hidden embedding of a GNN is claimed to subsume existing feature-, edge-, and weight-perturbation defenses, but the claim rests on simplifications that the experiments do not actually test.