AI Paper Atlas

Research map / Graph learning / GNN architectures

Imprint of the Forgotten: Stealthy Membership Inference in Unlearned Graph Neural Networks

He Zhang, Bang Wu, Xiaoning Liu, Karin Verspoor, Xun Yi

AAAI 2026 · Graph learning › GNN architectures · approach: Robustness, privacy, and fairness of GNNs · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use dual-encoder architecture with embedding loss instead of a plain MLP attack model (ablation)FMIA · Cora/CS/DBLP/PubMed x GCN/GAT/GINattack AUCImproved
remove encoder modules or swap embedding distance function (ablation)FMIA · PubMed GNNDeleteattack AUCImproved
increase amount of unlearned data under Fine-tuning (ablation)unlearned GNN vulnerability · Fine-tuning unlearningattack AUCHurt
increase amount of unlearned data under GIF (ablation)unlearned GNN vulnerability · GIF unlearningattack AUCNo clear effect
increase amount of unlearned data under GNNDelete (ablation)unlearned GNN vulnerability · GNNDelete unlearningattack AUCImproved
use deeper DeepGCN (56 layers vs 3) as target (ablation)unlearned GNN vulnerability · PubMed, Fine-tuningattack AUC (%): 96.18 -> 93.44Hurt
use attack model trained with a different unlearning method (GIF -> Fine-tuning) (ablation)FMIA · Fine-tuning targetattack AUC: 13.3%Hurt
use attack model trained on a different dataset or architecture (transfer) (ablation)FMIA · cross dataset and modelattack AUCMixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy