COLD is presented, 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.
Abstract
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.
Existing waveform-domain audio watermarks are robust to many conventional distortions but can degrade substantially under neural codec resynthesis. We investigate whether continuous neural codec latents provide a more suitable embedding space using a restricted formulation built around frozen pretrained EnCodec. To tes...
Lovro Brulec, Sahil Karawade, Leonard Kinzinger· arXiv.org· 0 citations
ClaW (Codec-guided Latent Watermarking) is proposed, a robust and efficient watermarking framework for traceable diffusion image generation with frozen diffusion backbones and inversion-free detection and achieves state-of-the-art robustness under image transformations, enabling reliable user-level traceability.
Huang-Chao Song, Ling-Yun Yu, Cong-Rong Li et al.· 0 citations
Recent advances in video generation have increased the demand for reliable watermarking for copyright protection, yet the robustness of video watermarks against removal attacks remains underexplored. Most watermark-removal methods originate from the image domain: signal optimization injects imperceptible pixel-domain p...
Yifan Liao, Zhen Sun, Zhi-Cong Huang et al.· 0 citations
Video steganography hides secret content inside video, but hiding a large payload while keeping the cover clean and the data secure remains difficult. This paper presents an encoder-decoder model that embeds a full RGB secret frame into a cover frame at 24 bits per pixel, frame by frame. The encoder joins the cover and...
Brwa O. Abdalla, O. Abdulhammed· UHD Journal of Science and T...· 0 citations
Audio watermarking is increasingly important for tracing generated speech. Several audio watermarking methods have been proposed to embed the watermark in various domains, such as waveform, timbre feature, or latent representations, for making the embedded watermark robust against traditional digital signal processing...
An-Nan Wu, Wen-Chin Huang, T. Toda· arXiv.org· 1 citation
The proliferation of high-fidelity generative editing models has made it possible to inject violent or sexual content into otherwise ordinary images while preserving visual plausibility, with concrete consequences for public discourse and vulnerable populations. We propose a robust semantic watermarking framework that...
Yoonseo Kim, S. Baek, Jun-Yong Park· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.