SKeDA: A Generative Watermarking Framework for Text-to-video Diffusion Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Yang, Zou, Xinze, Ma, Zehua, Fang, Han, Zhang, Weiming
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910035804684288
author Yang, Yang
Zou, Xinze
Ma, Zehua
Fang, Han
Zhang, Weiming
author_facet Yang, Yang
Zou, Xinze
Ma, Zehua
Fang, Han
Zhang, Weiming
contents The rise of text-to-video generation models has raised growing concerns over content authenticity, copyright protection, and malicious misuse. Watermarking serves as an effective mechanism for regulating such AI-generated content, where high fidelity and strong robustness are particularly critical. Recent generative image watermarking methods provide a promising foundation by leveraging watermark information and pseudo-random keys to control the initial sampling noise, enabling lossless embedding. However, directly extending these techniques to videos introduces two key limitations: Existing designs implicitly rely on strict alignment between video frames and frame-dependent pseudo-random binary sequences used for watermark encryption. Once this alignment is disrupted, subsequent watermark extraction becomes unreliable; and Video-specific distortions, such as inter-frame compression, significantly degrade watermark reliability. To address these issues, we propose SKeDA, a generative watermarking framework tailored for text-to-video diffusion models. SKeDA consists of two components: (1) Shuffle-Key-based Distribution-preserving Sampling (SKe) employs a single base pseudo-random binary sequence for watermark encryption and derives frame-level encryption sequences through permutation. This design transforms watermark extraction from synchronization-sensitive sequence decoding into permutation-tolerant set-level aggregation, substantially improving robustness against frame reordering and loss; and (2) Differential Attention (DA), which computes inter-frame differences and dynamically adjusts attention weights during extraction, enhancing robustness against temporal distortions. Extensive experiments demonstrate that SKeDA preserves high video generation quality and watermark robustness.
format Preprint
id arxiv_https___arxiv_org_abs_2603_00194
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle SKeDA: A Generative Watermarking Framework for Text-to-video Diffusion Models
Yang, Yang
Zou, Xinze
Ma, Zehua
Fang, Han
Zhang, Weiming
Computer Vision and Pattern Recognition
Artificial Intelligence
Cryptography and Security
The rise of text-to-video generation models has raised growing concerns over content authenticity, copyright protection, and malicious misuse. Watermarking serves as an effective mechanism for regulating such AI-generated content, where high fidelity and strong robustness are particularly critical. Recent generative image watermarking methods provide a promising foundation by leveraging watermark information and pseudo-random keys to control the initial sampling noise, enabling lossless embedding. However, directly extending these techniques to videos introduces two key limitations: Existing designs implicitly rely on strict alignment between video frames and frame-dependent pseudo-random binary sequences used for watermark encryption. Once this alignment is disrupted, subsequent watermark extraction becomes unreliable; and Video-specific distortions, such as inter-frame compression, significantly degrade watermark reliability. To address these issues, we propose SKeDA, a generative watermarking framework tailored for text-to-video diffusion models. SKeDA consists of two components: (1) Shuffle-Key-based Distribution-preserving Sampling (SKe) employs a single base pseudo-random binary sequence for watermark encryption and derives frame-level encryption sequences through permutation. This design transforms watermark extraction from synchronization-sensitive sequence decoding into permutation-tolerant set-level aggregation, substantially improving robustness against frame reordering and loss; and (2) Differential Attention (DA), which computes inter-frame differences and dynamically adjusts attention weights during extraction, enhancing robustness against temporal distortions. Extensive experiments demonstrate that SKeDA preserves high video generation quality and watermark robustness.
title SKeDA: A Generative Watermarking Framework for Text-to-video Diffusion Models
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Cryptography and Security
url https://arxiv.org/abs/2603.00194