PreGIP: Watermarking the Pretraining of Graph Neural Networks for Deep Intellectual Property Protection

TL;DR

PreGIP introduces a novel watermarking framework for pretraining GNNs, protecting intellectual property without compromising downstream task performance, and is resistant to fine-tuning attacks.

Contribution

It presents the first task-free watermarking method for self-supervised pretrained GNNs, ensuring IP protection while maintaining embedding quality.

Findings

Effective watermarking of pretrained GNNs demonstrated.

High resistance to fine-tuning attacks shown.

Maintains high performance on downstream tasks.

Abstract

Pretraining on Graph Neural Networks (GNNs) has shown great power in facilitating various downstream tasks. As pretraining generally requires huge amount of data and computational resources, the pretrained GNNs are high-value Intellectual Properties (IP) of the legitimate owner. However, adversaries may illegally copy and deploy the pretrained GNN models for their downstream tasks. Though initial efforts have been made to watermark GNN classifiers for IP protection, these methods require the target classification task for watermarking, and thus are not applicable to self-supervised pretraining of GNN models. Hence, in this work, we propose a novel framework named PreGIP to watermark the pretraining of GNN encoder for IP protection while maintain the high-quality of the embedding space. PreGIP incorporates a task-free watermarking loss to watermark the embedding space of pretrained GNN encoder. A finetuning-resistant watermark injection is further deployed. Theoretical analysis and extensive experiments show the effectiveness of {\method} in IP protection and maintaining high-performance for downstream tasks.