GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models | Paper Citation Record

Observation 859567cc-cc23-4c6e-ac44-ae7ada09e590 · outbound

This paper cites https://https://github.com/tkipf/gcn.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models https://https://github.com/tkipf/gcn

Reference 1

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.628706Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ec8a9235-3ebc-44ee-9f8d-4735646bc864 · outbound

This paper cites https://github.com/xinle ihe/link stealing attack.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models https://github.com/xinle ihe/link stealing attack

Reference 2

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.614600Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 120808fa-bf25-4455-9448-56ad8150e9be · outbound

This paper cites https://github.com/PetarV-/GAT, 2017.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models https://github.com/PetarV-/GAT, 2017

Reference 3

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.600863Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation f1b42a29-bcb4-4d36-b7c9-65b92ba5a44a · outbound

This paper cites Deep learning with differential privacy.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Deep learning with differential privacy

Reference 4

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.587413Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 1821cb71-28be-4a3b-baa9-6a9c907d35a7 · outbound

This paper cites Structural, Syntactic, and Statistical Pattern Recognition.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Structural, Syntactic, and Statistical Pattern Recognition

Reference 5

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.574728Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation c09b8231-b5d0-4474-93f0-0ee3c158deaf · outbound

This paper cites Extracting training data from large language models.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Extracting training data from large language models

Reference 6

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.561176Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 7b620eaf-64e4-4cf4-9448-dfe3196fb473 · outbound

This paper cites Exploring connections between active learning and model extraction.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Exploring connections between active learning and model extraction

Reference 7

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.547289Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation b8c62a11-7fdc-404d-9f8e-016d23e9119f · outbound

This paper cites Label-only membership inference attacks.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Label-only membership inference attacks

Reference 8

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.533308Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation dbcbb3da-204e-42b8-9451-969f5f054bd7 · outbound

This paper cites Distinguishing enzyme structures from non-enzymes without alignments.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Distinguishing enzyme structures from non-enzymes without alignments

Reference 9

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.518863Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 0394d47a-309c-4536-87c5-6b44552aa5b0 · outbound

This paper cites Inductive repre- sentation learning on large graphs.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Inductive repre- sentation learning on large graphs

Reference 10

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.504674Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 0882f329-d60a-4d9d-94b2-1fd348afa44e · outbound

This paper cites Stealing links from graph neural networks.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Stealing links from graph neural networks

Reference 11

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.490410Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation ac41a6bb-1007-4b66-a2a4-f0575081cf18 · outbound

This paper cites Node-Level Membership Inference Attacks Against Graph Neural Networks.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Node-Level Membership Inference Attacks Against Graph Neural Networks

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-10T18:53:15.745884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 050b672a-4f4a-4412-85a4-d97b175c5d9d · outbound

This paper cites Transmia: membership inference attacks using transfer shadow training.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Transmia: membership inference attacks using transfer shadow training

Reference 13

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.476823Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 9507c598-f29a-41d6-85af-55058cbd7bc5 · outbound

This paper cites High accuracy and high fidelity extraction of neural networks.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models High accuracy and high fidelity extraction of neural networks

Reference 14

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.463254Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 2d025f7a-0e0a-4619-aad4-8b13e2bd23d7 · outbound

This paper cites Memguard: Defending against black-box membership inference attacks via adversarial examples.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Memguard: Defending against black-box membership inference attacks via adversarial examples

Reference 15

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.449897Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e1b478fa-22ba-4680-815d-d01fd60011fe · outbound

This paper cites Semi-supervised classification with graph convolutional networks.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Semi-supervised classification with graph convolutional networks

Reference 16

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.436221Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation fbba1405-11b9-48ce-9cf0-2561366e9c34 · outbound

This paper cites Stolen memories: Leveraging model memorization for calibrated {White-Box} membership inference.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Stolen memories: Leveraging model memorization for calibrated {White-Box} membership inference

Reference 17

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.423474Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 49a3d0fd-2e0e-440d-afbc-50966cddc216 · outbound

This paper cites Membership inference attacks and defenses in classification models.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Membership inference attacks and defenses in classification models

Reference 18

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.410176Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 8131b299-e17e-4d43-bdc9-a44eb29f4b13 · outbound

This paper cites Membership leakage in label-only exposures.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Membership leakage in label-only exposures

Reference 19

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.396383Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation b01168dd-7a72-4e5e-8600-19240d1b6ced · outbound

This paper cites Encodermi: Membership inference against pre-trained encoders in contrastive learning.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Encodermi: Membership inference against pre-trained encoders in contrastive learning

Reference 20

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.382238Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 8d35d4e7-a166-4c00-b39c-e34cce40191f · outbound

This paper cites Devil in disguise: Breaching graph neural networks privacy through infiltration.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Devil in disguise: Breaching graph neural networks privacy through infiltration

Reference 21

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.368233Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 4a7b7c8d-2f36-48e4-a957-26b9e1e967c9 · outbound

This paper cites Comprehensive pri- vacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Comprehensive pri- vacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning

Reference 22

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.353546Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation e1108a70-6c65-4259-8ceb-3d16b9555098 · outbound

This paper cites Machine learning with membership privacy using adversarial regularization.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Machine learning with membership privacy using adversarial regularization

Reference 23

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.339234Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 0c76d516-9628-4637-b207-bd256fd72477 · outbound

This paper cites Membership inference attack on graph neural networks.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Membership inference attack on graph neural networks

Reference 24

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.323815Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 7a9d8cf0-5082-4499-8488-c6b325039568 · outbound

This paper cites White-box vs black-box: Bayes optimal strategies for membership inference.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models White-box vs black-box: Bayes optimal strategies for membership inference

Reference 25

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.307562Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 7d4a92d8-eed6-4f47-943d-a7da326aea72 · outbound

This paper cites Gap: Differentially private graph neural net- works with aggregation perturbation.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Gap: Differentially private graph neural net- works with aggregation perturbation

Reference 26

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.293015Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation dc8a0da1-8c50-413a-9129-c908bde357ca · outbound

This paper cites Gap: Differentially private graph neural net- works with aggregation perturbation.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Gap: Differentially private graph neural net- works with aggregation perturbation

Reference 27

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.278948Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 832e6fa3-b5e1-406e-8c5c-86c1b483c757 · outbound

This paper cites Updates-leak: Data set inference and reconstruction attacks in online learning.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Updates-leak: Data set inference and reconstruction attacks in online learning

Reference 28

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.264394Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 09245560-9fbe-468e-8e7d-187b7a30b1f2 · outbound

This paper cites Ml-leaks: Model and data independent membership inference attacks and defenses on machine learning models.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Ml-leaks: Model and data independent membership inference attacks and defenses on machine learning models

Reference 29

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.249700Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 221438e5-e3ce-491c-85b6-82d462af4bf1 · outbound

This paper cites The graph neural network model.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models The graph neural network model

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-10T18:53:15.824428Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d82605bf-397d-4c1a-9a69-f718c106564c · outbound

This paper cites Privacy-preserving deep learning.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Privacy-preserving deep learning

Reference 31

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.224845Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation df2fdb86-613c-4f51-8620-ce4524cc2115 · outbound

This paper cites Membership inference attacks against machine learning models.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Membership inference attacks against machine learning models

Reference 32

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.210878Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 155e0289-5145-43fd-8ea6-1fec7a705fde · outbound

This paper cites Information leakage in embedding models.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Information leakage in embedding models

Reference 33

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.197047Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 928cf93c-e313-4891-98ec-ddaa63316e1a · outbound

This paper cites Systematic evaluation of privacy risks of machine learning models.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Systematic evaluation of privacy risks of machine learning models

Reference 34

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.182774Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 35c97d71-cbb6-4115-94f8-6156f2a458d4 · outbound

This paper cites Privacy risks of securing machine learning models against adversarial examples.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Privacy risks of securing machine learning models against adversarial examples

Reference 35

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.168866Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 587865f1-24dc-400b-941b-2668c68164c4 · outbound

This paper cites Dropout: a simple way to prevent neural networks from overfitting.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Dropout: a simple way to prevent neural networks from overfitting

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-10T18:53:15.848999Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6c5a411f-a7a0-43b7-9e20-a1ad7fd426ad · outbound

This paper cites Stealing machine learning models via prediction {APIs}.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Stealing machine learning models via prediction {APIs}

Reference 37

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.146090Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 24763788-55c0-490f-aacd-818432e42799 · outbound

This paper cites Graph attention networks.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Graph attention networks

Reference 38

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.131340Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3726bf0a-b429-4758-8a99-ca2502e91e3d · outbound

This paper cites Stealing hyperparameters in machine learning.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Stealing hyperparameters in machine learning

Reference 39

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.117030Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 90359d8b-7d8d-4e90-8e82-cf2cf7b698ae · outbound

This paper cites Differentially private empirical risk minimization revisited: Faster and more general.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Differentially private empirical risk minimization revisited: Faster and more general

Reference 40

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.102174Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 9a26f239-2a31-471a-8cb5-eb46d11a6c95 · outbound

This paper cites Link membership inference at- tacks against unsupervised graph representation learning.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Link membership inference at- tacks against unsupervised graph representation learning

Reference 41

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.087529Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 4ca12d4f-e14e-4025-8824-b13accd41646 · outbound

This paper cites Semi-supervised classification with graph convolutional networks.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Semi-supervised classification with graph convolutional networks

Reference 42

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.072740Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 585f4f94-b7c6-422b-8fab-da6f4a667820 · outbound

This paper cites Vertex cover.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Vertex cover

Reference 43

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.057800Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation c091bcee-2c9d-4510-949d-b9a16171c08b · outbound

This paper cites Adapting membership inference attacks to gnn for graph classification: Ap- proaches and implications.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Adapting membership inference attacks to gnn for graph classification: Ap- proaches and implications

Reference 44

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.043869Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 8a3a91d1-aaeb-44c6-8c31-9376b755ad20 · outbound

This paper cites Linkteller: Recovering private edges from graph neural networks via influence analysis.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Linkteller: Recovering private edges from graph neural networks via influence analysis

Reference 45

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.029541Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 3e6d8192-7608-46df-a698-24196fde3cfc · outbound

This paper cites Link Stealing Attacks Against Inductive Graph Neural Networks.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Link Stealing Attacks Against Inductive Graph Neural Networks

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-10T18:53:15.890584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 61670f12-b490-450a-8f77-6dbcf0e91afe · outbound

This paper cites How powerful are graph neural networks? In International Conference on Learning Representations (ICLR) , 2019.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models How powerful are graph neural networks? In International Conference on Learning Representations (ICLR) , 2019

Reference 47

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:16.015151Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation 1df095e6-0dc3-403e-8309-85c1e65fadd1 · outbound

This paper cites Differentially private model publishing for deep learning.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Differentially private model publishing for deep learning

Reference 48

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:15.999261Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Observation d63a667c-6c81-4a76-8c0c-7425d25be10f · outbound

This paper cites Graph transformer networks.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Graph transformer networks

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-10T18:53:15.903618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a9583594-08aa-4f6e-a205-58bbf49e65d3 · outbound

This paper cites Demystifying uneven vulnerability of link stealing attacks against graph neural networks.

GRID: Protecting Training Graph from Link Stealing Attacks on GNN Models Demystifying uneven vulnerability of link stealing attacks against graph neural networks

Reference 50

Resolution: verified fuzzy; raw_fallback, observed 2026-08-10T18:53:15.975143Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.

Coverage vector

Reference resolution

Outbound references

Pith citing papers