SPDMark: Selective Parameter Displacement for Robust Video Watermarking

• URL: http://arxiv.org/abs/2512.12090v1
• Date: Fri, 12 Dec 2025 23:35:13 GMT
• Title: SPDMark: Selective Parameter Displacement for Robust Video Watermarking
• Authors: Samar Fares, Nurbek Tastan, Karthik Nandakumar,
• Abstract summary: This work introduces a novel framework for in-generation video watermarking called SPDMark.<n>Watermarks are embedded into the generated videos by modifying a subset of parameters in the generative model.<n> Evaluations on both text-to-video and image-to-video generation models demonstrate the ability of SPDMark to generate imperceptible watermarks.
• Score: 30.398519705830264
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The advent of high-quality video generation models has amplified the need for robust watermarking schemes that can be used to reliably detect and track the provenance of generated videos. Existing video watermarking methods based on both post-hoc and in-generation approaches fail to simultaneously achieve imperceptibility, robustness, and computational efficiency. This work introduces a novel framework for in-generation video watermarking called SPDMark (pronounced `SpeedMark') based on selective parameter displacement of a video diffusion model. Watermarks are embedded into the generated videos by modifying a subset of parameters in the generative model. To make the problem tractable, the displacement is modeled as an additive composition of layer-wise basis shifts, where the final composition is indexed by the watermarking key. For parameter efficiency, this work specifically leverages low-rank adaptation (LoRA) to implement the basis shifts. During the training phase, the basis shifts and the watermark extractor are jointly learned by minimizing a combination of message recovery, perceptual similarity, and temporal consistency losses. To detect and localize temporal modifications in the watermarked videos, we use a cryptographic hashing function to derive frame-specific watermark messages from the given base watermarking key. During watermark extraction, maximum bipartite matching is applied to recover the correct frame order, even from temporally tampered videos. Evaluations on both text-to-video and image-to-video generation models demonstrate the ability of SPDMark to generate imperceptible watermarks that can be recovered with high accuracy and also establish its robustness against a variety of common video modifications.

Related papers

• SKeDA: A Generative Watermarking Framework for Text-to-video Diffusion Models [40.540302276054376]
  We propose a generative watermarking framework tailored for text-to-video diffusion models.<n> SKeDA consists of two components: (1) Shuffle-Key-based Distribution-preserving Sampling (SKe) employs a single base pseudo-random binary sequence for watermark encryption and derives frame-level encryption sequences through permutation.<n>Extensive experiments demonstrate that SKeDA preserves high video generation quality and watermark robustness.
  arXiv  Detail & Related papers  (2026-02-27T06:18:03Z)
• OSI: One-step Inversion Excels in Extracting Diffusion Watermarks [56.210696479553945]
  We propose One-step Inversion (OSI), a significantly faster and more accurate method for extracting Gaussian Shading style watermarks.<n>OSI reformulates watermark extraction as a learnable sign classification problem, which eliminates the need for precise regression of the initial noise.<n>Our OSI substantially outperforms the multi-step diffusion inversion method: it is 20x faster, achieves higher extraction accuracy, and doubles the watermark payload capacity.
  arXiv  Detail & Related papers  (2026-02-10T07:43:16Z)
• WaTeRFlow: Watermark Temporal Robustness via Flow Consistency [46.206343565195375]
  We present WaTeRFlow, a framework tailored for robustness under I2V.<n>It exposes the encoder-decoder to realistic distortions via instruction-driven edits and a fast video diffusion proxy during training.<n>Experiments across representative I2V models show accurate watermark recovery from frames, with higher first-frame and per-frame bit accuracy and resilience.
  arXiv  Detail & Related papers  (2025-12-22T05:33:59Z)
• Detecting Post-generation Edits to Watermarked LLM Outputs via Combinatorial Watermarking [51.417096446156926]
  We introduce a new task: detecting post-generation edits locally made to watermarked LLM outputs.<n>We propose a pattern-based watermarking framework, which partitions the vocabulary into disjoint subsets and embeds the watermark.<n>We evaluate our method on open-source LLMs across a variety of editing scenarios, demonstrating strong empirical performance in edit localization.
  arXiv  Detail & Related papers  (2025-10-02T03:33:12Z)
• Safe-Sora: Safe Text-to-Video Generation via Graphical Watermarking [88.89887962002207]
  invisible generative watermarking remains largely underexplored in video generation.<n>We propose Safe-Sora, the first framework to embed graphical watermarks directly into the video generation process.<n>We show that Safe-Sora achieves state-of-the-art performance in terms of video quality, watermark fidelity, and robustness.
  arXiv  Detail & Related papers  (2025-05-19T03:31:31Z)
• VideoMark: A Distortion-Free Robust Watermarking Framework for Video Diffusion Models [18.427936201177122]
  VideoMark is a distortion-free robust watermarking framework for video diffusion models.<n>We employ a frame-wise watermarking strategy with pseudorandom error correction (PRC) codes, using a fixed watermark sequence.<n>For watermark extraction, we propose a Temporal Matching Module (TMM) that leverages edit distance to align decoded messages with the original watermark sequence.
  arXiv  Detail & Related papers  (2025-04-23T02:21:12Z)
• VideoShield: Regulating Diffusion-based Video Generation Models via Watermarking [27.345134138673945]
  VideoShield is a novel watermarking framework for video generation models.<n>Unlike post-processing methods, VideoShield embeds watermarks directly during video generation.<n>To ensure video integrity, we introduce a tamper localization feature.
  arXiv  Detail & Related papers  (2025-01-24T02:57:09Z)
• Video Seal: Open and Efficient Video Watermarking [47.40833588157406]
  Video watermarking addresses challenges by embedding imperceptible signals into videos, allowing for identification.<n>Video Seal is a comprehensive framework for neural video watermarking and a competitive open-sourced model.<n>We present experimental results demonstrating the effectiveness of the approach in terms of speed, imperceptibility, and robustness.
  arXiv  Detail & Related papers  (2024-12-12T17:41:49Z)
• LVMark: Robust Watermark for Latent Video Diffusion Models [13.85241328100336]
  We introduce LVMark, a novel watermarking method for video diffusion models.<n>We propose a new watermark decoder tailored for generated videos by learning the consistency between adjacent frames.<n>We optimize both the watermark decoder and the latent decoder of diffusion model, effectively balancing the trade-off between visual quality and bit accuracy.
  arXiv  Detail & Related papers  (2024-12-12T09:57:20Z)
• An Unforgeable Publicly Verifiable Watermark for Large Language Models [84.2805275589553]
  Current watermark detection algorithms require the secret key used in the watermark generation process, making them susceptible to security breaches and counterfeiting during public detection. We propose an unforgeable publicly verifiable watermark algorithm named UPV that uses two different neural networks for watermark generation and detection, instead of using the same key at both stages.
  arXiv  Detail & Related papers  (2023-07-30T13:43:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.