Papers
arxiv:2605.09203

Removing the Watermark Is Not Enough: Forensic Stealth in Generative-AI Watermark Removal

Published on May 9
Authors:
,

Abstract

Current AI watermark removal techniques fail to achieve true forensic stealth, as they either preserve detectable signals or compromise image quality, highlighting the need for methods that simultaneously evade watermarks, maintain utility, and remain indistinguishable from original content.

Watermarks for AI-generated images are meant to support downstream decisions about provenance, manipulation, and trust. In the settings that motivate watermark removal, therefore, success means more than causing the watermark test to fail. A successful remover must also preserve the utility of the image and make the output forensically indistinguishable from clean content, so that defeating the verifier restores deniability rather than merely replacing one detection signal with another. We show that current watermark removal attacks fail this stronger objective. Across six state-of-the-art removers spanning four attack families, independent forensic detectors distinguish removal-processed outputs from clean images at over 98% true-positive rate under a 1% false-positive budget. Thus, current removers often replace the watermark with a different detectable signal. Using UnMarker (IEEE S&P 2025) as a detailed case study, we show that this signal persists under common post-processing, exhibits a characteristic two-regime spectral deformation, and yields a three-way tension among removal success, image quality, and forensic stealth. These results show that existing removal benchmarks are incomplete: they reward verifier evasion and utility preservation while omitting forensic stealth. A workable watermark remover must satisfy all three conditions at once: watermark evasion, utility preservation, and forensic indistinguishability from clean content.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2605.09203
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2605.09203 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2605.09203 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2605.09203 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.