arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.04435cs.LGcs.AI
收藏

PreGIP:为深度知识产权保护对图神经网络预训练进行水印标记

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

Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));The Pennsylvania State University(宾夕法尼亚州立大学)

Enyan Dai, Minhua Lin, Suhang Wang

AI总结:

本文提出PreGIP框架,通过任务无关的水印损失和抗微调水印注入,在不损害嵌入空间质量的前提下保护GNN预训练模型的知识产权。

摘要:

图神经网络(GNNs)的预训练已在促进各种下游任务方面展现出强大能力。由于预训练通常需要海量数据和计算资源,预训练后的GNN是合法所有者的高价值知识产权(IP)。然而,攻击者可能非法复制并部署预训练GNN模型用于其下游任务。尽管已有初步工作尝试为GNN分类器添加水印以进行IP保护,但这些方法需要目标分类任务才能进行水印标记,因此不适用于GNN模型的自监督预训练。为此,本文提出一个名为PreGIP的新框架,在对GNN编码器预训练进行水印标记以实现IP保护的同时,保持嵌入空间的高质量。PreGIP引入一种与任务无关的水印损失,对预训练GNN编码器的嵌入空间进行水印标记,并进一步部署了抗微调的水印注入机制。理论分析和大量实验表明,PreGIP在IP保护以及保持下游任务高性能方面具有有效性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑