Content Seal is a state-of-the-art framework for invisible, robust watermarking across all modalities audio, image, video, and text. This suite spans the entire generative lifecycle, from training data and inference to generated media.
See the codeREADME
Content Seal is a comprehensive framework for invisible, robust watermarking across all modalities — audio, image, video, and text. It spans the entire generative AI lifecycle, from training data and inference to generated media, providing state-of-the-art tools for content provenance and authentication.
Contents
Post-Hoc Watermarking
Watermarks applied after content generation by any model or system — model-agnostic and universal across all content types.
Content Seal for Images and Video
Content Seal Image is deployed at scale for Muse Image with a custom proprietary implementation. We also provide open-source versions of our research models for images and video, readily available to download.
| Research | Links |
|---|---|
| Pixel Seal: Adversarial-Only Training for Invisible Image and Video Watermarking Flagship image & video watermarking model, SOTA in robustness and imperceptibility, built with a more stable adversarial-only training paradigm. |   |
| We Can Hide More Bits: The Unused Watermarking Capacity in Theory and in Practice Bigger model with 4× capacity boost to 1024 bits while preserving quality and robustness. |  |
| Video Seal: Open and Efficient Video Watermarking Extension of image watermarking models to video, resilient to editing and video codecs. |  |
| Watermark Anything with Localized Messages Embed (possibly multiple) localized watermarks into images; survives inpainting and splicing attacks. | |
| Geometric Image Synchronization with Deep Watermarking Robust image synchronization, enabling reversal of geometric transformations applied to an image. | |
Content Seal for Audio
| Research | Links |
|---|---|
| Proactive Detection of Voice Cloning with Localized Watermarking Localized audio watermarking with sample-level detection and streaming support for real-time applications. | |
Content Seal for Text
| Research | Links |
|---|---|
| How Good is Post-Hoc Watermarking With Language Model Rephrasing? Comprehensive evaluation framework for post-hoc text watermarking with LLM rephrasing. | |
In-Model and Generation-Time Watermarking
Watermarks embedded during content generation by modifying model behavior or latent representations.
Content Seal for Text
| Research | Links |
|---|---|
| TextSeal: A Localized LLM Watermark for Provenance & Distillation Protection SOTA LLM watermark with dual-key Gumbel-max sampling, entropy-weighted scoring, and multi-region localization. Distortion-free, preserves reasoning and benchmark performance, detectable when diluted in human text, radioactive through distillation. | |
Content Seal for Image & Audio
| Research | Links |
|---|---|
| Learning to Watermark in the Latent Space of Generative Models Unified latent-space watermarking that enables 20× speedup over pixel methods and secures open-source models via in-model distillation. | |
| The Stable Signature: Rooting Watermarks in Latent Diffusion Models Roots the watermark in the model's latent decoder for tracing the outputs of latent generative models. | |
| Watermarking Autoregressive Image Generation Watermarking for autoregressive image generation models. | |
Radioactivity
| Research | Links |
|---|---|
| Watermarking Makes Language Models Radioactive Detects if a language model was trained on synthetic text by finding weak residuals of watermark signals in fine-tuned LLMs — high-confidence even when as little as 5% of training text is watermarked. | |
| Detecting Benchmark Contamination Through Watermarking Watermarks benchmarks before release to detect if models were trained on test sets, using theoretically grounded statistical tests while preserving benchmark utility. | |
Watermark Security
Research on adversarial attacks and defenses for watermarking systems through red teaming.
| Research | Links |
|---|---|
| Transferable Black-Box One-Shot Forging of Watermarks via Image Preference Models Black-box watermark forging using image preference models for red-teaming watermarking systems. | |
License
The code is licensed under an MIT license.
Contributors
25 commits
1 commits
Similar repos
Languages
HTML
49.9%
CSS
35.9%
JavaScript
14.2%
Content Seal is a state-of-the-art framework for invisible, robust watermarking across all modalities audio, image, video, and text. This suite spans the entire generative lifecycle, from training data and inference to generated media.
See the codeREADME
Content Seal is a comprehensive framework for invisible, robust watermarking across all modalities — audio, image, video, and text. It spans the entire generative AI lifecycle, from training data and inference to generated media, providing state-of-the-art tools for content provenance and authentication.
Contents
Post-Hoc Watermarking
Watermarks applied after content generation by any model or system — model-agnostic and universal across all content types.
Content Seal for Images and Video
Content Seal Image is deployed at scale for Muse Image with a custom proprietary implementation. We also provide open-source versions of our research models for images and video, readily available to download.
| Research | Links |
|---|---|
| Pixel Seal: Adversarial-Only Training for Invisible Image and Video Watermarking Flagship image & video watermarking model, SOTA in robustness and imperceptibility, built with a more stable adversarial-only training paradigm. | |
| We Can Hide More Bits: The Unused Watermarking Capacity in Theory and in Practice Bigger model with 4× capacity boost to 1024 bits while preserving quality and robustness. | |
| Video Seal: Open and Efficient Video Watermarking Extension of image watermarking models to video, resilient to editing and video codecs. | |
| Watermark Anything with Localized Messages Embed (possibly multiple) localized watermarks into images; survives inpainting and splicing attacks. | |
| Geometric Image Synchronization with Deep Watermarking Robust image synchronization, enabling reversal of geometric transformations applied to an image. | |
Content Seal for Audio
| Research | Links |
|---|---|
| Proactive Detection of Voice Cloning with Localized Watermarking Localized audio watermarking with sample-level detection and streaming support for real-time applications. | |
Content Seal for Text
| Research | Links |
|---|---|
| How Good is Post-Hoc Watermarking With Language Model Rephrasing? Comprehensive evaluation framework for post-hoc text watermarking with LLM rephrasing. | |
In-Model and Generation-Time Watermarking
Watermarks embedded during content generation by modifying model behavior or latent representations.
Content Seal for Text
| Research | Links |
|---|---|
| TextSeal: A Localized LLM Watermark for Provenance & Distillation Protection SOTA LLM watermark with dual-key Gumbel-max sampling, entropy-weighted scoring, and multi-region localization. Distortion-free, preserves reasoning and benchmark performance, detectable when diluted in human text, radioactive through distillation. | |
Content Seal for Image & Audio
| Research | Links |
|---|---|
| Learning to Watermark in the Latent Space of Generative Models Unified latent-space watermarking that enables 20× speedup over pixel methods and secures open-source models via in-model distillation. | |
| The Stable Signature: Rooting Watermarks in Latent Diffusion Models Roots the watermark in the model's latent decoder for tracing the outputs of latent generative models. | |
| Watermarking Autoregressive Image Generation Watermarking for autoregressive image generation models. | |
Radioactivity
| Research | Links |
|---|---|
| Watermarking Makes Language Models Radioactive Detects if a language model was trained on synthetic text by finding weak residuals of watermark signals in fine-tuned LLMs — high-confidence even when as little as 5% of training text is watermarked. | |
| Detecting Benchmark Contamination Through Watermarking Watermarks benchmarks before release to detect if models were trained on test sets, using theoretically grounded statistical tests while preserving benchmark utility. | |
Watermark Security
Research on adversarial attacks and defenses for watermarking systems through red teaming.
| Research | Links |
|---|---|
| Transferable Black-Box One-Shot Forging of Watermarks via Image Preference Models Black-box watermark forging using image preference models for red-teaming watermarking systems. | |
License
The code is licensed under an MIT license.
Similar repos
Contributors
25 commits
1 commits
Languages
HTML
49.9%
CSS
35.9%
JavaScript
14.2%