Transferable Watermarking to Self-supervised Pre-trained Graph Encoders by Trigger Embeddings

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhao, Xiangyu, Wu, Hanzhou, Zhang, Xinpeng
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909418821517312
author Zhao, Xiangyu
Wu, Hanzhou
Zhang, Xinpeng
author_facet Zhao, Xiangyu
Wu, Hanzhou
Zhang, Xinpeng
contents Recent years have witnessed the prosperous development of Graph Self-supervised Learning (GSSL), which enables to pre-train transferable foundation graph encoders. However, the easy-to-plug-in nature of such encoders makes them vulnerable to copyright infringement. To address this issue, we develop a novel watermarking framework to protect graph encoders in GSSL settings. The key idea is to force the encoder to map a set of specially crafted trigger instances into a unique compact cluster in the outputted embedding space during model pre-training. Consequently, when the encoder is stolen and concatenated with any downstream classifiers, the resulting model inherits the `backdoor' of the encoder and predicts the trigger instances to be in a single category with high probability regardless of the ground truth. Experimental results have shown that, the embedded watermark can be transferred to various downstream tasks in black-box settings, including node classification, link prediction and community detection, which forms a reliable watermark verification system for GSSL in reality. This approach also shows satisfactory performance in terms of model fidelity, reliability and robustness.
format Preprint
id arxiv_https___arxiv_org_abs_2406_13177
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Transferable Watermarking to Self-supervised Pre-trained Graph Encoders by Trigger Embeddings
Zhao, Xiangyu
Wu, Hanzhou
Zhang, Xinpeng
Cryptography and Security
Recent years have witnessed the prosperous development of Graph Self-supervised Learning (GSSL), which enables to pre-train transferable foundation graph encoders. However, the easy-to-plug-in nature of such encoders makes them vulnerable to copyright infringement. To address this issue, we develop a novel watermarking framework to protect graph encoders in GSSL settings. The key idea is to force the encoder to map a set of specially crafted trigger instances into a unique compact cluster in the outputted embedding space during model pre-training. Consequently, when the encoder is stolen and concatenated with any downstream classifiers, the resulting model inherits the `backdoor' of the encoder and predicts the trigger instances to be in a single category with high probability regardless of the ground truth. Experimental results have shown that, the embedded watermark can be transferred to various downstream tasks in black-box settings, including node classification, link prediction and community detection, which forms a reliable watermark verification system for GSSL in reality. This approach also shows satisfactory performance in terms of model fidelity, reliability and robustness.
title Transferable Watermarking to Self-supervised Pre-trained Graph Encoders by Trigger Embeddings
topic Cryptography and Security
url https://arxiv.org/abs/2406.13177