mlsanityData to 7 Oct 2026

GENIE: Watermarking Graph Neural Networks for Link Prediction

arXiv 2406.04805 ↗First posted 7 Jun 2024cs.CR cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

The rapid adoption, usefulness, and resource-intensive training of Graph Neural Network (GNN) models have made them an invaluable intellectual property in graph-based machine learning. However, their wide-spread adoption also makes them susceptible to stealing, necessitating robust Ownership Demonstration (OD) techniques. Watermarking is a promising OD framework for deep neural networks, but existing methods fail to generalize to GNNs due to the non-Euclidean nature of graph data. Existing works on GNN watermarking primarily focus on node and graph classification, overlooking Link Prediction (LP). In this paper, we propose GENIE (watermarking Graph nEural Networks for lInk prEdiction), the first scheme to watermark GNNs for LP. GENIE creates a novel backdoor for both node-representation and subgraph-based LP methods, utilizing a unique trigger set and a secret watermark vector. Our OD scheme is equipped with Dynamic Watermark Thresholding (DWT), ensuring high verification probability while addressing practical issues in existing OD schemes. We extensively evaluate GENIE across 4 diverse model architectures (i.e., SEAL, GCN, GraphSAGE and NeoGNN), 7 real-world datasets and 21 watermark removal techniques and demonstrate its robustness to watermark removal and ownership piracy attacks. Finally, we discuss adaptive attacks against GENIE and a defense strategy to counter it. The codebase and related artifacts are publicly available at our Project Page.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 47 of its 114 references that are in the map. First posted on arXiv 7 Jun 2024.

Builds on

47 of 114 references.

References · 47

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  5. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  6. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  7. 2017Graph Attention Networkscited by 8,854
  8. 2017Inductive Representation Learning on Large Graphscited by 6,284
  9. 2018How Powerful are Graph Neural Networks?cited by 4,355
  10. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  11. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 1,998
  12. 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
35 more
  1. 2014How transferable are features in deep neural networks?cited by 1,216
  2. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,133
  3. 2018Pitfalls of Graph Neural Network Evaluationcited by 994
  4. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
  5. 2018Link Prediction Based on Graph Neural Networkscited by 829
  6. 2021A Survey of Quantization Methods for Efficient Neural Network Inferencecited by 798
  7. 2019Graph Neural Networks for Social Recommendationcited by 711
  8. 2019Multi-scale Attributed Node Embeddingcited by 543
  9. 2020Backdoor Learning: A Surveycited by 412
  10. 2018Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooringcited by 334
  11. 2023A critical look at the evaluation of GNNs under heterophily: Are we really making progress?cited by 332
  12. 2021Graph Neural Network for Traffic Forecasting: A Surveycited by 260
  13. 2019PyTorch-BigGraph: A Large-scale Graph Embedding Systemcited by 118
  14. 2020Graph Backdoorcited by 112
  15. 2018Billion-scale Commodity Embedding for E-commerce Recommendation in Alibabacited by 105
  16. 2019DAWN: Dynamic Adversarial Watermarking of Neural Networkscited by 94
  17. 2022Neo-GNNs: Neighborhood Overlap-aware Graph Neural Networks for Link Predictioncited by 78
  18. 2021A survey of deep neural network watermarking techniquescited by 69
  19. 2023Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarkingcited by 69
  20. 2021SoK: How Robust is Image Classification Deep Neural Network Watermarking? (Extended Version)cited by 67
  21. 2020Challenges in Benchmarking Stream Learning Algorithms with Real-world Datacited by 57
  22. 2021Model Stealing Attacks Against Inductive Graph Neural Networkscited by 50
  23. 2020A Systematic Review on Model Watermarking for Neural Networkscited by 49
  24. 2021Explainability-based Backdoor Attacks Against Graph Neural Networkscited by 42
  25. 2021An Overview of Backdoor Attacks Against Deep Neural Networks and Possible Defencescited by 41
  26. 2020Model Extraction Attacks on Graph Neural Networks: Taxonomy and Realizationcited by 39
  27. 2021Watermarking Graph Neural Networks based on Backdoor Attackscited by 25
  28. 2020Watermarking Graph Neural Networks by Random Graphscited by 23
  29. 2019Adversarial Model Extraction on Graph Neural Networkscited by 22
  30. 2023False Claims against Model Ownership Resolutioncited by 17
  31. 2023GrOVe: Ownership Verification of Graph Neural Networks using Embeddingscited by 16
  32. 2024MEA-Defender: A Robust Watermark against Model Extraction Attackcited by 16
  33. 2022Link-Backdoor: Backdoor Attack on Link Prediction via Node Injectioncited by 10
  34. 2021Dyn-Backdoor: Backdoor Attack on Dynamic Link Predictioncited by 4
  35. 2019Kernel Density Estimation Bias under Minimal Assumptionscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2026CITED: A Decision Boundary-Aware Signature for GNNs Towards Model Extraction Defensecited by 3
  2. 2025Intellectual Property in Graph-Based Machine Learning as a Service: Attacks and Defensescited by 2
  3. 2025WGLE:Backdoor-free and Multi-bit Black-box Watermarking for Graph Neural Networkscited by 1