Graph Watermarks
Xiaohan Zhao, Qingyun Liu, Lin Zhou, Haitao Zheng, Ben Y. Zhao

TL;DR
This paper introduces graph watermarks as a novel method for protecting sensitive graph datasets by embedding unique, robust watermarks that can identify leaks and deter unauthorized sharing.
Contribution
It proposes a new graph watermarking scheme that is robust, difficult to forge, and suitable for large real-world graphs, addressing limitations of existing privacy-preserving tools.
Findings
Watermarks are unique and hard to forge.
The scheme is robust against single and colluding attackers.
Experimental results show high resilience and utility.
Abstract
From network topologies to online social networks, many of today's most sensitive datasets are captured in large graphs. A significant challenge facing owners of these datasets is how to share sensitive graphs with collaborators and authorized users, e.g. network topologies with network equipment vendors or Facebook's social graphs with academic collaborators. Current tools can provide limited node or edge privacy, but require modifications to the graph that significantly reduce its utility. In this work, we propose a new alternative in the form of graph watermarks. Graph watermarks are small graphs tailor-made for a given graph dataset, a secure graph key, and a secure user key. To share a sensitive graph G with a collaborator C, the owner generates a watermark graph W using G, the graph key, and C's key as input, and embeds W into G to form G'. If G' is leaked by C,its owner can…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsInternet Traffic Analysis and Secure E-voting · Network Security and Intrusion Detection · Advanced Graph Neural Networks
