Safe-Sora: Safe Text-to-Video Generation via Graphical Watermarking

• URL: http://arxiv.org/abs/2505.12667v1
• Date: Mon, 19 May 2025 03:31:31 GMT
• Title: Safe-Sora: Safe Text-to-Video Generation via Graphical Watermarking
• Authors: Zihan Su, Xuerui Qiu, Hongbin Xu, Tangyu Jiang, Junhao Zhuang, Chun Yuan, Ming Li, Shengfeng He, Fei Richard Yu,
• Abstract summary: Safe-Sora is the first framework to embed graphical watermarks directly into the video generation process.<n>We develop a 3D wavelet transform-enhanced Mamba architecture with a adaptive localtemporal scanning strategy.<n>Experiments demonstrate Safe-Sora achieves state-of-the-art performance in terms of video quality, watermark fidelity, and robustness.
• Score: 53.434260110195446
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The explosive growth of generative video models has amplified the demand for reliable copyright preservation of AI-generated content. Despite its popularity in image synthesis, invisible generative watermarking remains largely underexplored in video generation. To address this gap, we propose Safe-Sora, the first framework to embed graphical watermarks directly into the video generation process. Motivated by the observation that watermarking performance is closely tied to the visual similarity between the watermark and cover content, we introduce a hierarchical coarse-to-fine adaptive matching mechanism. Specifically, the watermark image is divided into patches, each assigned to the most visually similar video frame, and further localized to the optimal spatial region for seamless embedding. To enable spatiotemporal fusion of watermark patches across video frames, we develop a 3D wavelet transform-enhanced Mamba architecture with a novel spatiotemporal local scanning strategy, effectively modeling long-range dependencies during watermark embedding and retrieval. To the best of our knowledge, this is the first attempt to apply state space models to watermarking, opening new avenues for efficient and robust watermark protection. Extensive experiments demonstrate that Safe-Sora achieves state-of-the-art performance in terms of video quality, watermark fidelity, and robustness, which is largely attributed to our proposals. We will release our code upon publication.

Related papers

• Optimization-Free Universal Watermark Forgery with Regenerative Diffusion Models [50.73220224678009]
  Watermarking can be used to verify the origin of synthetic images generated by artificial intelligence models.<n>Recent studies demonstrate the capability to forge watermarks from a target image onto cover images via adversarial techniques.<n>In this paper, we uncover a greater risk of an optimization-free and universal watermark forgery.<n>Our approach significantly broadens the scope of attacks, presenting a greater challenge to the security of current watermarking techniques.
  arXiv  Detail & Related papers  (2025-06-06T12:08:02Z)
• Video Signature: In-generation Watermarking for Latent Video Diffusion Models [19.648332041264474]
  Video Signature (VID SIG) is an in-generation watermarking method for latent video diffusion models.<n>We achieve this by partially fine-tuning the latent decoder, where Perturbation-Aware Suppression (PAS) pre-identifies and freezes perceptually sensitive layers to preserve visual quality.<n> Experimental results show that VID SIG achieves the best overall performance in watermark extraction, visual quality, and generation efficiency.
  arXiv  Detail & Related papers  (2025-05-31T17:43:54Z)
• Spread them Apart: Towards Robust Watermarking of Generated Content [4.332441337407564]
  We propose an approach to embed watermarks into the generated content to allow future detection of the generated content and identification of the user who generated it.<n>We prove that watermarks embedded are guaranteed to be robust against additive perturbations of a bounded magnitude.
  arXiv  Detail & Related papers  (2025-02-11T09:23:38Z)
• On the Coexistence and Ensembling of Watermarks [93.15379331904602]
  We find that various open-source watermarks can coexist with only minor impacts on image quality and decoding robustness.<n>We show how ensembling can increase the overall message capacity and enable new trade-offs between capacity, accuracy, robustness and image quality, without needing to retrain the base models.
  arXiv  Detail & Related papers  (2025-01-29T00:37:06Z)
• RoboSignature: Robust Signature and Watermarking on Network Attacks [0.5461938536945723]
  We present a novel adversarial fine-tuning attack that disrupts the model's ability to embed the intended watermark.<n>Our findings emphasize the importance of anticipating and defending against potential vulnerabilities in generative systems.
  arXiv  Detail & Related papers  (2024-12-22T04:36:27Z)
• Video Seal: Open and Efficient Video Watermarking [47.40833588157406]
  Video watermarking addresses challenges by embedding imperceptible signals into videos, allowing for identification.<n>Video Seal is a comprehensive framework for neural video watermarking and a competitive open-sourced model.<n>We present experimental results demonstrating the effectiveness of the approach in terms of speed, imperceptibility, and robustness.
  arXiv  Detail & Related papers  (2024-12-12T17:41:49Z)
• LVMark: Robust Watermark for Latent Video Diffusion Models [13.85241328100336]
  We introduce LVMark, a novel watermarking method for video diffusion models.<n>We propose a new watermark decoder tailored for generated videos by learning the consistency between adjacent frames.<n>We optimize both the watermark decoder and the latent decoder of diffusion model, effectively balancing the trade-off between visual quality and bit accuracy.
  arXiv  Detail & Related papers  (2024-12-12T09:57:20Z)
• Certifiably Robust Image Watermark [57.546016845801134]
  Generative AI raises many societal concerns such as boosting disinformation and propaganda campaigns. Watermarking AI-generated content is a key technology to address these concerns. We propose the first image watermarks with certified robustness guarantees against removal and forgery attacks.
  arXiv  Detail & Related papers  (2024-07-04T17:56:04Z)
• RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable Guarantees [33.61946642460661]
  This paper introduces a robust and agile watermark detection framework, dubbed as RAW. We employ a classifier that is jointly trained with the watermark to detect the presence of the watermark. We show that the framework provides provable guarantees regarding the false positive rate for misclassifying a watermarked image.
  arXiv  Detail & Related papers  (2024-01-23T22:00:49Z)
• T2IW: Joint Text to Image & Watermark Generation [74.20148555503127]
  We introduce a novel task for the joint generation of text to image and watermark (T2IW) This T2IW scheme ensures minimal damage to image quality when generating a compound image by forcing the semantic feature and the watermark signal to be compatible in pixels. We demonstrate remarkable achievements in image quality, watermark invisibility, and watermark robustness, supported by our proposed set of evaluation metrics.
  arXiv  Detail & Related papers  (2023-09-07T16:12:06Z)
• Watermarking Images in Self-Supervised Latent Spaces [75.99287942537138]
  We revisit watermarking techniques based on pre-trained deep networks, in the light of self-supervised approaches. We present a way to embed both marks and binary messages into their latent spaces, leveraging data augmentation at marking time.
  arXiv  Detail & Related papers  (2021-12-17T15:52:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.