mlsanityData to 14 Oct 2026

Robust GNN Watermarking via Implicit Perception of Topological Invariants

arXiv 2510.25934 ↗First posted 29 Oct 2025cs.LG cs.CRcited by 0

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) are valuable intellectual property, yet many watermarks rely on backdoor triggers that break under common model edits and create ownership ambiguity. We present InvGNN-WM, which ties ownership to a model's implicit perception of a graph invariant, enabling trigger-free, black-box verification with negligible task impact. A lightweight head predicts normalized algebraic connectivity on an owner-private carrier set; a sign-sensitive decoder outputs bits, and a calibrated threshold controls the false-positive rate. Across diverse node and graph classification datasets and backbones, InvGNN-WM matches clean accuracy while yielding higher watermark accuracy than trigger- and compression-based baselines. It remains strong under unstructured pruning, fine-tuning, and post-training quantization; plain knowledge distillation (KD) weakens the mark, while KD with a watermark loss (KD+WM) restores it. We provide guarantees for imperceptibility and robustness, and we prove that exact removal is NP-complete.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 27 references that are in the map. First posted on arXiv 29 Oct 2025.

Builds on

19 of 27 references.

References · 19

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  3. 2017Inductive Representation Learning on Large Graphscited by 6,320
  4. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  5. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  6. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  7. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,636
  8. 2019Simplifying Graph Convolutional Networkscited by 1,477
  9. 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
  10. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 976
  11. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 728
  12. 2018Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooringcited by 357
7 more
  1. 2017Embedding Watermarks into Deep Neural Networkscited by 248
  2. 2020GraphLIME: Local Interpretable Model Explanations for Graph Neural Networkscited by 209
  3. 2017Adversarial Frontier Stitching for Remote Neural Network Watermarkingcited by 118
  4. 2022Certified Neural Network Watermarks with Randomized Smoothingcited by 41
  5. 2020Neural Network Laundering: Removing Black-Box Backdoor Watermarks from Deep Neural Networkscited by 27
  6. 2021Watermarking Graph Neural Networks based on Backdoor Attackscited by 25
  7. 2025Watermarking Graph Neural Networks via Explanations for Ownership Protectioncited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025WGLE:Backdoor-free and Multi-bit Black-box Watermarking for Graph Neural Networks
  2. 2024GENIE: Watermarking Graph Neural Networks for Link Prediction
  3. 2026A Robust Watermark-based Fingerprint Framework for GNNs Ownership Verification
  4. 2026DRGW: Learning Disentangled Representations for Robust Graph Watermarking
  5. 2026GraphIP-Bench: How Hard Is It to Steal a Graph Neural Network, and Can We Stop It?
  6. 2024PreGIP: Watermarking the Pretraining of Graph Neural Networks for Deep Intellectual Property Protection
  7. 2024DeepiSign-G: Generic Watermark to Stamp Hidden DNN Parameters for Self-contained Tracking
  8. 2025Persistence of Backdoor-based Watermarks for Neural Networks: A Comprehensive Evaluation