Low-Compute Watermark Removal via Dual-Domain Natural Projection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Meshram, Pragati Shuddhodhan, Chandrasekaran, Varun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917508624154624
author Meshram, Pragati Shuddhodhan
Chandrasekaran, Varun
author_facet Meshram, Pragati Shuddhodhan
Chandrasekaran, Varun
contents Effective removal of semantic watermarks requires balancing three competing objectives: \emph{high removal success}, \emph{low perceptual distortion}, and \emph{low computational cost}. However, existing single-image attacks typically optimize only for the first two, achieving strong watermark suppression but relying on expensive, multi-step optimization that limits practical deployment. In this work, we show that this trade-off is fundamental: no current approach achieves all three properties simultaneously. We introduce \textsc{DAWN}, a lightweight, training-free attack that explicitly targets the low-cost regime while maintaining competitive removal performance. \textsc{DAWN} works by projecting a watermarked image onto natural-image priors in complementary frequency and semantic spaces, suppressing watermark signals that deviate from natural statistics, and then applying a decoupled perceptual-alignment step to restore visual consistency with minimal artifact. Across diverse pixel-, frequency-, and latent-space watermarking schemes, \textsc{DAWN} consistently reduces detectability while preserving structural and semantic fidelity, demonstrating that efficient, low-resource watermark removal is feasible with only modest perceptual degradation. Our code is available at https://github.com/Pragati-Meshram/DAWN.
format Preprint
id arxiv_https___arxiv_org_abs_2510_07538
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Low-Compute Watermark Removal via Dual-Domain Natural Projection
Meshram, Pragati Shuddhodhan
Chandrasekaran, Varun
Computer Vision and Pattern Recognition
Effective removal of semantic watermarks requires balancing three competing objectives: \emph{high removal success}, \emph{low perceptual distortion}, and \emph{low computational cost}. However, existing single-image attacks typically optimize only for the first two, achieving strong watermark suppression but relying on expensive, multi-step optimization that limits practical deployment. In this work, we show that this trade-off is fundamental: no current approach achieves all three properties simultaneously. We introduce \textsc{DAWN}, a lightweight, training-free attack that explicitly targets the low-cost regime while maintaining competitive removal performance. \textsc{DAWN} works by projecting a watermarked image onto natural-image priors in complementary frequency and semantic spaces, suppressing watermark signals that deviate from natural statistics, and then applying a decoupled perceptual-alignment step to restore visual consistency with minimal artifact. Across diverse pixel-, frequency-, and latent-space watermarking schemes, \textsc{DAWN} consistently reduces detectability while preserving structural and semantic fidelity, demonstrating that efficient, low-resource watermark removal is feasible with only modest perceptual degradation. Our code is available at https://github.com/Pragati-Meshram/DAWN.
title Low-Compute Watermark Removal via Dual-Domain Natural Projection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2510.07538