paper-with-me

홈 › Papers

The Forensic Cost of Watermark Removal: From Dedicated Attacks to Image Editing

2026-04-28 · Gautier Evennou, Ewa Kijak arxiv

Current watermark removal methods are evaluated on two axes: attack success rate and perceptual quality. We show this is insufficient. While state-of-the-art attacks successfully degrade the watermark signal without visible distortion, they leave distinct statistical artifacts that betray the removal attempt. We name this overlooked axis Watermark Removal Detection (WRD) and demonstrate that a modern classifier trained on these artifacts achieves state-of-the-art detection rates at $10^{-3}$ FPR across every removal method tested. No existing attack accounts for this forensic leakage. We benchmark leading watermarking schemes against standard removal pipelines under the extended evaluation triple of attack success, perceptual quality, and forensic detectability, and find that no current method balances all three. Our results establish forensic stealthiness as a necessary requirement for watermark removal.

📄 PDF Abstract BibTeX arXiv:2604.25491

Code (0)

등록된 구현이 없습니다.

Tasks

Image Editing

Similar Papers 제목 키워드 기반

Class-feature Watermark: A Resilient Black-box Watermark Against Model Extraction Attacks

2025-11-11 · Yaxin Xiao, Qingqing Ye, Zi Liang, Haoyang Li 외 arxiv

Machine learning models constitute valuable intellectual property, yet remain vulnerable to model extraction attacks (MEA), where adversaries replicate their functionality through black-box queries. Model watermarking co…

Model extraction

SoK: How Robust is Image Classification Deep Neural Network Watermarking? (Extended Version)

2021-08-11 · Nils Lukas, Edward Jiang, Xinda Li, Florian Kerschbaum

Deep Neural Network (DNN) watermarking is a method for provenance verification of DNN models. Watermarking should be robust against watermark removal attacks that derive a surrogate model that evades provenance verificat…

image-classificationImage Classification

On Function-Coupled Watermarks for Deep Neural Networks

2023-02-08 · Xiangyu Wen, Yu Li, Wei Jiang, Qiang Xu

Well-performed deep neural networks (DNNs) generally require massive labelled data and computational resources for training. Various watermarking techniques are proposed to protect such intellectual properties (IPs), whe…

image-classificationImage Classification

Towards Robust Model Watermark via Reducing Parametric Vulnerability

2023-09-09 · ICCV 2023 1 · Guanhao Gan, Yiming Li, Dongxian Wu, Shu-Tao Xia

Deep neural networks are valuable assets considering their commercial benefits and huge demands for costly annotation and computation resources. To protect the copyright of DNNs, backdoor-based ownership verification bec…

model

Towards Robust Content Watermarking Against Removal and Forgery Attacks

2026-04-08 · Yifan Zhu, Yihan Wang, Xiao-Shan Gao arxiv

Generated contents have raised serious concerns about copyright protection, image provenance, and credit attribution. A potential solution for these problems is watermarking. Recently, content watermarking for text-to-im…