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

arXiv: https://arxiv.org/abs/2505.12667 · HTML: https://mlsanity.com/paper/2505.12667/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Watermarking generated content and models, one of 12 directions in LLM safety and security.
- Builds on 48 of its 64 references that are in the map.
- First posted on arXiv 19 May 2025.

## Placed in

- LLM safety and security / [Watermarking generated content and models](https://mlsanity.com/safety/watermarking-generated-content-and-models/)

## Builds on (most cited first, 30 of 48)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Towards Accurate Generative Models of Video: A New Metric & Challenges](https://mlsanity.com/paper/1812.01717/) (2018)
- [VMamba: Visual State Space Model](https://mlsanity.com/paper/2401.10166/) (2024)
- [Simplified State Space Layers for Sequence Modeling](https://mlsanity.com/paper/2208.04933/) (2022)
- [ModelScope Text-to-Video Technical Report](https://mlsanity.com/paper/2308.06571/) (2023)
- [Open-Sora: Democratizing Efficient Video Production for All](https://mlsanity.com/paper/2412.20404/) (2024)
- [VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models](https://mlsanity.com/paper/2401.09047/) (2024)
- [Latte: Latent Diffusion Transformer for Video Generation](https://mlsanity.com/paper/2401.03048/) (2024)
- [DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors](https://mlsanity.com/paper/2310.12190/) (2023)
- [Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers](https://mlsanity.com/paper/2402.19479/) (2024)
- [VideoMamba: State Space Model for Efficient Video Understanding](https://mlsanity.com/paper/2403.06977/) (2024)
- [The Stable Signature: Rooting Watermarks in Latent Diffusion Models](https://mlsanity.com/paper/2303.15435/) (2023)
- [An Empirical Study of Mamba-based Language Models](https://mlsanity.com/paper/2406.07887/) (2024)
- [Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models](https://mlsanity.com/paper/2404.04956/) (2024)
- [A Recipe for Watermarking Diffusion Models](https://mlsanity.com/paper/2303.10137/) (2023)
- [VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models](https://mlsanity.com/paper/2403.06098/) (2024)
- [RingID: Rethinking Tree-Ring Watermarking for Enhanced Multi-Key Identification](https://mlsanity.com/paper/2404.14055/) (2024)
- [MambaByte: Token-free Selective State Space Model](https://mlsanity.com/paper/2401.13660/) (2024)
- [FreqMamba: Viewing Mamba from a Frequency Perspective for Image Deraining](https://mlsanity.com/paper/2404.09476/) (2024)

## Built on by (most cited first, 11 of 11)

- [Stochastic Self-Guidance for Training-Free Enhancement of Diffusion Models](https://mlsanity.com/paper/2508.12880/) (2025)
- [Generation Enhances Understanding in Unified Multimodal Models via Multi-Representation Generation](https://mlsanity.com/paper/2601.21406/) (2026)
- [ConsistentRFT: Reducing Visual Hallucinations in Flow-based Reinforcement Fine-Tuning](https://mlsanity.com/paper/2602.03425/) (2026)
- [ViStoryBench: Comprehensive Benchmark Suite for Story Visualization](https://mlsanity.com/paper/2505.24862/) (2025)
- [Video Signature: Implicit Watermarking for Video Diffusion Models](https://mlsanity.com/paper/2506.00652/) (2025)
- [EasyTune: Efficient Step-Aware Fine-Tuning for Diffusion-Based Motion Generation](https://mlsanity.com/paper/2602.07967/) (2026)
- [SVL: Empowering Spiking Neural Networks for Efficient 3D Open-World Understanding](https://mlsanity.com/paper/2505.17674/) (2025)
- [LoT-Pass: Long-term-robust Image Watermarking for Image to Video Generation](https://mlsanity.com/paper/2509.17773/) (2025)
- [Where and When to Force: Routed Forcing for Streaming Avatars](https://mlsanity.com/paper/2609.30963/) (2026)
- [Rethinking Visual Provenance: Detection and Watermarking Across Direct Visual Generation and LLM-Driven Code Rendering](https://mlsanity.com/paper/2610.08137/) (2026)
- [Getting Space Right: Agentic Rewards for Image Generation](https://mlsanity.com/paper/2610.14852/) (2026)

## Abstract (arXiv)

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. Code is publicly available at https://github.com/Sugewud/Safe-Sora