Pith. sign in

REVIEW 1 cited by

Stable Signature is Unstable: Removing Image Watermark from Diffusion Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2405.07145 v1 pith:SL736QAZ submitted 2024-05-12 cs.CR cs.CV

classification cs.CRcs.CV
keywords watermarkdiffusionimagesstablegeneratedsignaturemodelattack
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Watermark has been widely deployed by industry to detect AI-generated images. A recent watermarking framework called \emph{Stable Signature} (proposed by Meta) roots watermark into the parameters of a diffusion model's decoder such that its generated images are inherently watermarked. Stable Signature makes it possible to watermark images generated by \emph{open-source} diffusion models and was claimed to be robust against removal attacks. In this work, we propose a new attack to remove the watermark from a diffusion model by fine-tuning it. Our results show that our attack can effectively remove the watermark from a diffusion model such that its generated images are non-watermarked, while maintaining the visual quality of the generated images. Our results highlight that Stable Signature is not as stable as previously thought.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Watermarking across Modalities for Content Tracing and Generative AI

    cs.CR 2025-02 conditional novelty 3.0 of 10

    A thesis showing that invisible watermarks can be embedded across images, audio, text, and model weights, with statistical tests for tracing AI-generated content.

Pith tools