LVMark: Robust Watermark for Latent Video Diffusion Models

TL;DR

LVMark is a new watermarking technique for video diffusion models that maintains temporal consistency, minimizes quality loss, and ensures robustness against distortions, thereby protecting model ownership.

Contribution

We introduce LVMark, a novel watermarking method that learns temporal consistency and balances visual quality with robustness for video diffusion models.

Findings

Achieves robust watermark decoding with 512-bit capacity.

Maintains high video quality with minimal degradation.

Ensures robustness against various video distortions.

Abstract

Rapid advancements in video diffusion models have enabled the creation of realistic videos, raising concerns about unauthorized use and driving the demand for techniques to protect model ownership. Existing watermarking methods, while effective for image diffusion models, do not account for temporal consistency, leading to degraded video quality and reduced robustness against video distortions. To address this issue, we introduce LVMark, a novel watermarking method for video diffusion models. We propose a new watermark decoder tailored for generated videos by learning the consistency between adjacent frames. It ensures accurate message decoding, even under malicious attacks, by combining the low-frequency components of the 3D wavelet domain with the RGB features of the video. Additionally, our approach minimizes video quality degradation by embedding watermark messages in layers with minimal impact on visual appearance using an importance-based weight modulation strategy. We optimize both the watermark decoder and the latent decoder of diffusion model, effectively balancing the trade-off between visual quality and bit accuracy. Our experiments show that our method embeds invisible watermarks into video diffusion models, ensuring robust decoding accuracy with 512-bit capacity, even under video distortions.