[2512.12090] SPDMark: Selective Parameter Displacement for Robust Video Watermarking

Computer Science > Computer Vision and Pattern Recognition arXiv:2512.12090 (cs) [Submitted on 12 Dec 2025 (v1), last revised 1 Apr 2026 (this version, v2)] Title:SPDMark: Selective Parameter Displacement for Robust Video Watermarking Authors:Samar Fares, Nurbek Tastan, Karthik Nandakumar View a PDF of the paper titled SPDMark: Selective Parameter Displacement for Robust Video Watermarking, by Samar Fares and 2 other authors View PDF HTML (experimental) 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...