diffusion models 1frequency domain 1frequency-domain constraints 1image processing 1image restoration 1invisible watermark removal 1Mamba architecture 1semantic prior guidance 1state-space modeling 1watermark removal 1wavelet decomposition 1
From the 2 of 3 linked papers with an AI index.
3 papers
cs.CV2026
SPFM-Net: Semantic-Prior-Guided Frequency-Constrained Mamba for Invisible Watermark Attack
Chunpeng Wang, Yanan Shi, Zhiqiu Xia +3
The paper introduces SPFM-Net, a neural network that uses semantic priors, frequency constraints, and a lightweight Mamba-based state‑space module to remove invisible watermarks fr…
cs.CV2026
FDDWAN: A Frequency-Decoupled Diffusion Network for Watermarking Attack
Chunpeng Wang, Yuxin Li, Xiaoyu Wang +3
The paper introduces FDDWAN, a two-stage neural network that removes invisible watermarks by first decomposing images with wavelets and then refining residuals with a diffusion mod…
cs.CV2026
Breaking Watermarks in the Frequency Domain: A Modulated Diffusion Attack Framework
Chunpeng Wang, Binyan Qu, Xiaoyu Wang +4
Digital image watermarking has advanced rapidly for copyright protection of generative AI, yet the comparatively limited progress in watermark attack techniques has broken the atta…