Pith. sign in

REVIEW 11 cited by

Robust Invisible Video Watermarking with Attention

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1909.01285 v1 pith:SSVOB5O6 submitted 2019-09-03 cs.MM cs.CV

Kevin Alex Zhang , Lei Xu , Alfredo Cuesta-Infante , Kalyan Veeramachaneni This is my paper · ORCID
classification cs.MMcs.CV
keywords videowatermarkingrobustableachieveadversarialallowingarbitrary
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

The goal of video watermarking is to embed a message within a video file in a way such that it minimally impacts the viewing experience but can be recovered even if the video is redistributed and modified, allowing media producers to assert ownership over their content. This paper presents RivaGAN, a novel architecture for robust video watermarking which features a custom attention-based mechanism for embedding arbitrary data as well as two independent adversarial networks which critique the video quality and optimize for robustness. Using this technique, we are able to achieve state-of-the-art results in deep learning-based video watermarking and produce watermarked videos which have minimal visual distortion and are robust against common video processing operations.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Moir\'e Video Authentication: A Physical Signature Against AI Video Generation

    cs.CV 2026-04 conditional novelty 7.5 of 10

    Fringe phase and grating image displacement are linearly coupled by optics in real video (the Moiré motion invariant) but not in AI-generated video, enabling physics-based authentication.

  2. Robust Watermarks Leak: Channel-Aware Feature Extraction Enables Adversarial Watermark Manipulation

    cs.CV 2025-02 conditional novelty 7.0 of 10

    Robust watermarks leak detectable patterns into neural network feature channels, enabling single-image, no-box watermark removal and forgery.

  3. ResGuard: Enhancing Robustness Against Known Original Attacks in Deep Watermarking

    cs.CV 2026-04 accept novelty 6.5 of 10

    ResGuard makes deep-watermark residuals image-specific via a contrastive loss and KOA noise layer, restoring near-perfect extraction under residual-subtraction attacks that previously collapsed accuracy to chance.

  4. AnchorMark: Robust Diffusion Watermarking via Latent-Space Rotation Synchrony

    cs.CR 2026-07 conditional novelty 6.0 of 10

    Image rotation is shown to rotate the recovered latent by the same angle, and a central phase anchor exploits this to estimate and undo rotation before decoding the watermark.

  5. Correlation-Aware and Gaussianity-Preserving Robust Latent Angular Watermarking for Diffusion Models

    cs.CV 2026-07 reject novelty 6.0 of 10

    LAW encodes watermark bits as ±90° angular offsets between latent noise pairs and claims Gaussianity preservation, but its own construction forces exact orthogonality that makes it detectable.

  6. ShapeMark: Robust and Diversity-Preserving Watermarking for Diffusion Models

    cs.CR 2026-03 conditional novelty 6.0 of 10

    ShapeMark embeds watermark bits as block-level permutations of a key-derived Gaussian noise latent, achieving higher robustness and diversity than prior noise-as-watermark methods.

  7. MarkSplatter: Generalizable Watermarking for 3D Gaussian Splatting Model via Splatter Image Structure

    cs.CV 2025-08 conditional novelty 6.0 of 10

    MarkSplatter embeds arbitrary messages into 3D Gaussian Splatting models in one forward pass via Splatter Image conversion, reaching about 94% bit-level accuracy at about 2.5 seconds per model.

  8. A Crack in the Bark: Leveraging Public Knowledge to Remove Tree-Ring Watermarks

    cs.CR 2025-06 conditional novelty 6.0 of 10

    VAE-recovered latent surrogates make Tree-Ring watermarks removable: ROC-AUC drops from 0.993 to 0.153 with little image quality loss.

  9. Training-Free Watermarking for Autoregressive Image Generation

    cs.CV 2025-05 conditional novelty 6.0 of 10

    IndexMark watermarks images from autoregressive models by replacing similar codebook tokens with green tokens, then detecting the green-token rate after reconstruction.

  10. BiSLW: Bi-Spectral Latent Watermarking for Generative Diffusion Models

    cs.CV 2026-07 conditional novelty 5.5 of 10

    Learned dual-band DCT watermarking of diffusion latents improves PSNR by ~3 dB over prior latent methods while keeping near-perfect bit accuracy under regeneration and distortions.

  11. Retrieval-Driven Training-Free AI-Generated Video Attribution

    cs.CV 2026-07 conditional novelty 5.0 of 10

    A training-free retrieval pipeline using adaptive color transforms, multi-scale quantized residuals, and temporal aggregation attributes AI-generated videos to one of eight generators with 84.6% Rank-1 and 78.3% mAP o...

Pith tools