Watermarking Graph Neural Networks based on Backdoor Attacks. (arXiv:2110.11024v5 [cs.LG] UPDATED)

Graph Neural Networks (GNNs) have achieved promising performance in various
real-world applications. Building a powerful GNN model is not a trivial task,
as it requires a large amount of training data, powerful computing resources,
and human expertise in fine-tuning the model. Moreover, with the development of
adversarial attacks, e.g., model stealing attacks, GNNs raise challenges to
model authentication. To avoid copyright infringement on GNNs, verifying the
ownership of the GNN models is necessary.

This paper presents a watermarking framework for …

attacks backdoor networks neural networks watermarking