GUISE: Graph GaUssIan Shading watErmark

TL;DR

This paper introduces GUISE, a watermarking method adapted for molecular graph generation using latent 3D graph diffusion, ensuring content protection without compromising model performance.

Contribution

It adapts Gaussian Shading watermarking to the domain of molecular graph diffusion, enabling robust, lossless watermarking for complex graph-based AI models.

Findings

Watermarked molecules retain statistical properties in 9 out of 10 metrics.

Achieves 100% detection and 99% extraction rates.

Demonstrates robustness against post-editing attacks.

Abstract

In the expanding field of generative artificial intelligence, integrating robust watermarking technologies is essential to protect intellectual property and maintain content authenticity. Traditionally, watermarking techniques have been developed primarily for rich information media such as images and audio. However, these methods have not been adequately adapted for graph-based data, particularly molecular graphs. Latent 3D graph diffusion(LDM-3DG) is an ascendant approach in the molecular graph generation field. This model effectively manages the complexities of molecular structures, preserving essential symmetries and topological features. We adapt the Gaussian Shading, a proven performance lossless watermarking technique, to the latent graph diffusion domain to protect this sophisticated new technology. Our adaptation simplifies the watermark diffusion process through duplication and padding, making it adaptable and suitable for various message types. We conduct several experiments using the LDM-3DG model on publicly available datasets QM9 and Drugs, to assess the robustness and effectiveness of our technique. Our results demonstrate that the watermarked molecules maintain statistical parity in 9 out of 10 performance metrics compared to the original. Moreover, they exhibit a 100% detection rate and a 99% extraction rate in a 2D decoded pipeline, while also showing robustness against post-editing attacks.