mlsanityData to 7 Oct 2026

COPYCOP: Ownership Verification for Graph Neural Networks

arXiv 2605.05360 ↗First posted 6 May 2026cs.LG cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Given two GNNs that output node embeddings, how can we determine if they were trained independently? An adversary could have trained one GNN specifically to mimic the other GNN's embeddings. To obscure this relationship between the GNNs, the adversarial GNN might then transform its output embeddings. The two GNNs could have different architectures, weights, and embedding dimensions, and the adversary can transform the embeddings. Despite these stringent conditions, our algorithm (named CopyCop) can identify such copycat GNNs, unlike existing watermarking and fingerprinting methods. We also provide theoretical guarantees for CopyCop. Finally, experiments on 14 datasets and 5 GNN architectures demonstrate that CopyCop is accurate and robust against a broad class of adversarial attacks and transformations. Code is available at: https://anonymous.4open.science/r/CopyCop-Graph-Ownership-Verification-8143/README.md

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 27 of its 34 references that are in the map. First posted on arXiv 6 May 2026.

Builds on

27 of 34 references.

References · 27

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Inductive Representation Learning on Large Graphscited by 6,284
  3. 2018How Powerful are Graph Neural Networks?cited by 4,355
  4. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  5. 2019MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixingcited by 442
  6. 2018Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooringcited by 334
  7. 2017Embedding Watermarks into Deep Neural Networkscited by 227
  8. 2020GNNGuard: Defending Graph Neural Networks against Adversarial Attackscited by 195
  9. 2019Graph Neural Networks with convolutional ARMA filterscited by 185
  10. 2018PRADA: Protecting against DNN Model Stealing Attackscited by 159
  11. 2019Thieves on Sesame Street! Model Extraction of BERT-based APIscited by 136
  12. 2022A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainabilitycited by 118
15 more
  1. 2021Dataset Inference: Ownership Resolution in Machine Learningcited by 115
  2. 2019Deep Neural Network Fingerprinting by Conferrable Adversarial Examplescited by 90
  3. 2021SoK: How Robust is Image Classification Deep Neural Network Watermarking? (Extended Version)cited by 67
  4. 2023Are You Copying My Model? Protecting the Copyright of Large Language Models for EaaS via Backdoor Watermarkcited by 61
  5. 2022Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbationscited by 58
  6. 2021Model Stealing Attacks Against Inductive Graph Neural Networkscited by 50
  7. 2021Watermarking Graph Neural Networks based on Backdoor Attackscited by 25
  8. 2020Watermarking Graph Neural Networks by Random Graphscited by 23
  9. 2019Adversarial Model Extraction on Graph Neural Networkscited by 22
  10. 2022Group Property Inference Attacks Against Graph Neural Networkscited by 21
  11. 2023GrOVe: Ownership Verification of Graph Neural Networks using Embeddingscited by 16
  12. 2022GARNET: Reduced-Rank Topology Learning for Robust and Scalable Graph Neural Networkscited by 14
  13. 2022PublicCheck: Public Integrity Verification for Services of Run-time Deep Modelscited by 5
  14. 2023Securing Graph Neural Networks in MLaaS: A Comprehensive Realization of Query-based Integrity Verificationcited by 5
  15. 2024PreGIP: Watermarking the Pretraining of Graph Neural Networks for Deep Intellectual Property Protectioncited by 2

Built on by

Not cited yet.