KGMark: A Diffusion Watermark for Knowledge Graphs
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913897766715392 |
|---|---|
| author | Peng, Hongrui Lu, Haolang Yu, Yuanlong Fu, Weiye Wang, Kun Nan, Guoshun |
| author_facet | Peng, Hongrui Lu, Haolang Yu, Yuanlong Fu, Weiye Wang, Kun Nan, Guoshun |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_23873 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | KGMark: A Diffusion Watermark for Knowledge Graphs Peng, Hongrui Lu, Haolang Yu, Yuanlong Fu, Weiye Wang, Kun Nan, Guoshun Cryptography and Security Artificial Intelligence 68T07 I.2.8 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. |
| title | KGMark: A Diffusion Watermark for Knowledge Graphs |
| topic | Cryptography and Security Artificial Intelligence 68T07 I.2.8 |
| url | https://arxiv.org/abs/2505.23873 |