KGMark: A Diffusion Watermark for Knowledge Graphs

TL;DR

KGMARK introduces a novel graph watermarking framework for dynamic knowledge graphs, employing clustering, redundancy, and learnable masks to ensure robustness, transparency, and adaptability against spatial and temporal variations.

Contribution

It is the first framework to generate diffusion watermarks for dynamic knowledge graphs, addressing spatial and temporal variations with innovative methods.

Findings

Effective watermark robustness demonstrated on public benchmarks.

Enhanced transparency through learnable mask matrices.

Resilience against various attacks on dynamic graphs.

Abstract

Knowledge graphs (KGs) are ubiquitous in numerous real-world applications, and watermarking facilitates protecting intellectual property and preventing potential harm from AI-generated content. Existing watermarking methods mainly focus on static plain text or image data, while they can hardly be applied to dynamic graphs due to spatial and temporal variations of structured data. This motivates us to propose KGMARK, the first graph watermarking framework that aims to generate robust, detectable, and transparent diffusion fingerprints for dynamic KG data. Specifically, we propose a novel clustering-based alignment method to adapt the watermark to spatial variations. Meanwhile, we present a redundant embedding strategy to harden the diffusion watermark against various attacks, facilitating the robustness of the watermark to the temporal variations. Additionally, we introduce a novel learnable mask matrix to improve the transparency of diffusion fingerprints. By doing so, our KGMARK properly tackles the variation challenges of structured data. Experiments on various public benchmarks show the effectiveness of our proposed KGMARK. Our code is available at https://github.com/phrara/kgmark.