DRGW: Learning Disentangled Representations for Robust Graph Watermarking

TL;DR

DRGW introduces a novel graph watermarking framework using disentangled representation learning, adversarial training, and invertible neural networks to enhance robustness, transparency, and detectability of watermarks in graph data.

Contribution

It is the first to leverage disentangled representations and invertible neural networks for robust, transparent graph watermarking, addressing limitations of previous methods.

Findings

DRGW outperforms existing methods on benchmark datasets.

Watermarks are more robust against structural perturbations.

High detectability and transparency are achieved through the proposed framework.

Abstract

Graph-structured data is foundational to numerous web applications, and watermarking is crucial for protecting their intellectual property and ensuring data provenance. Existing watermarking methods primarily operate on graph structures or entangled graph representations, which compromise the transparency and robustness of watermarks due to the information coupling in representing graphs and uncontrollable discretization in transforming continuous numerical representations into graph structures. This motivates us to propose DRGW, the first graph watermarking framework that addresses these issues through disentangled representation learning. Specifically, we design an adversarially trained encoder that learns an invariant structural representation against diverse perturbations and derives a statistically independent watermark carrier, ensuring both robustness and transparency of watermarks. Meanwhile, we devise a graph-aware invertible neural network to provide a lossless channel for watermark embedding and extraction, guaranteeing high detectability and transparency of watermarks. Additionally, we develop a structure-aware editor that resolves the issue of latent modifications into discrete graph edits, ensuring robustness against structural perturbations. Experiments on diverse benchmark datasets demonstrate the superior effectiveness of DRGW.