# COVER: Codec-Robust Video Watermarking with Generative Video Priors

arXiv: https://arxiv.org/abs/2609.26236 · HTML: https://mlsanity.com/paper/2609.26236/

## Key facts

- Cited by 1 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 18 of its 35 references that are in the map.
- First posted on arXiv 17 Sep 2026.

## 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, 18 of 18)

- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [HiDDeN: Hiding Data With Deep Networks](https://mlsanity.com/paper/1807.09937/) (2018)
- [DVC: An End-to-end Deep Video Compression Framework](https://mlsanity.com/paper/1812.00101/) (2018)
- [StegaStamp: Invisible Hyperlinks in Physical Photographs](https://mlsanity.com/paper/1904.05343/) (2019)
- [Robust Invisible Video Watermarking with Attention](https://mlsanity.com/paper/1909.01285/) (2019)
- [Gaussian Shading: Provable Performance-Lossless Image Watermarking for Diffusion Models](https://mlsanity.com/paper/2404.04956/) (2024)
- [MBRS : Enhancing Robustness of DNN-based Watermarking by Mini-Batch of Real and Simulated JPEG Compression](https://mlsanity.com/paper/2108.08211/) (2021)
- [WAVES: Benchmarking the Robustness of Image Watermarks](https://mlsanity.com/paper/2401.08573/) (2024)
- [Distortion Agnostic Deep Watermarking](https://mlsanity.com/paper/2001.04580/) (2020)
- [Image and Video Compression with Neural Networks: A Review](https://mlsanity.com/paper/1904.03567/) (2019)
- [RoSteALS: Robust Steganography using Autoencoder Latent Space](https://mlsanity.com/paper/2304.03400/) (2023)
- [Video Seal: Open and Efficient Video Watermarking](https://mlsanity.com/paper/2412.09492/) (2024)
- [LaWa: Using Latent Space for In-Generation Image Watermarking](https://mlsanity.com/paper/2408.05868/) (2024)
- [ROMark: A Robust Watermarking System Using Adversarial Training](https://mlsanity.com/paper/1910.01221/) (2019)
- [VideoMark: A Distortion-Free Robust Watermarking Framework for Video Diffusion Models](https://mlsanity.com/paper/2504.16359/) (2025)
- [GaussMarker: Robust Dual-Domain Watermark for Diffusion Models](https://mlsanity.com/paper/2506.11444/) (2025)
- [Provenance Verification of AI-Generated Images via a Perceptual Hash Registry Anchored on Blockchain](https://mlsanity.com/paper/2602.02412/) (2026)
- [Unifying Watermarking via Dimension-Aware Mapping](https://mlsanity.com/paper/2602.03373/) (2026)

## Built on by (most cited first, 1 of 1)

- [Rethinking Visual Provenance: Detection and Watermarking Across Direct Visual Generation and LLM-Driven Code Rendering](https://mlsanity.com/paper/2610.08137/) (2026)

## Abstract (arXiv)

Video watermarking underpins copyright protection and provenance for generated media, yet almost every video is compressed by a codec before it is stored or shared. A codec discards precisely the perceptually redundant components that most watermarks rely on, so the payload is often lost even when the marked video looked flawless beforehand. Existing methods leave this path open, since they treat compression as one entry in a generic list of distortions, while a real codec is not differentiable and cannot enter gradient-based training. We present COVER, the first learned video watermark built around codec compression as its design target, which survives that compression by embedding the payload in the latent space of a frozen generative video autoencoder and recovering it by re-encoding the received video into that same latent space. To make codec robustness trainable, we build a differentiable codec surrogate bank that simulates the dominant degradation modes of practical compression, and we train the embedder and the latent decoder through three shared recovery paths under a fidelity objective that constrains the residual in the pixel and frequency domains. Across four codecs at 12 settings, COVER attains 93.72% average bit accuracy, ranks first on 11 of the 12, improves the strongest prior method by 2.68 points, and lifts the worst operating point from 68.90% to 73.72% while each marked video stays visually close to the source clip that produced it.