The DOI matches its Crossref record, with a small difference in title or year.
Tree-Rings Watermarks: Invisible Fingerprints for Diffusion Images
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Tree-Ring Watermarking proposes embedding a watermark in the initial noise vector of diffusion sampling, structured in Fourier space for robustness to a range of transformations, with detection performed by inverting the diffusion process to recover the noise signal.
“Tree-Ring Watermarking proposes embedding a watermark in the initial noise vector of diffusion sampling, structured in Fourier space for robustness to a range of transformations, with detection performed by inverting the diffusion process to recover the noise signal [32].”
From A Review of Tools and Technologies to Combat Deepfakes (2026) · cites this paper as [32]
Citations
Cited by
Sorted by citations
A Review of Tools and Technologies to Combat Deepfakes
Erokhin, D., & Komendantova, N. (2026) · Information · doi:10.3390/info17040347 · Cited by 3
Metadata
- Authors
- Wen, Y., Kirchenbauer, J., Geiping, J., & Goldstein, T.
- Venue
- Advances in Neural Information Processing Systems 36
- Published
- 2023
- Pages
- 58047-58063
- ISSN
- 1049-5258 (ISSN-L)
- OpenAlex
- W7133208273
- Cited by
- 70
- References
- 0
- Citations by year
- 2026: 65 · 2025: 5
- FWCI
- 122.98
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- neural information processing systems (publishedVersion)
- Topics
- Physical Sciences › Earth and Planetary Sciences › Atmospheric Science › Tree-ring climate responses
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Steganography and Watermarking Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Image and Signal Denoising Methods
- Keywords
- diffusion models, watermarking, invisible watermarking, image forensics
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
