# Watermark Detection on FFHQ

Source: [Watermark Detection on FFHQ](<https://www.sota2.com/research/sota/watermark-detection-on-ffhq>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:59:02.694Z

Evaluation of watermark detection performance on the FFHQ dataset, reporting Precision/Utility (Pu) metrics across various thresholds (R=0% to R=100%).

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Watermark Detection |
| Dataset (including any stated split) | FFHQ |
| Metric | Pu (R=0) |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 2 of 2 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Pu (R=0)](<https://www.sota2.com/research/sota/watermark-detection-on-ffhq.md?metric=Pu%20(R%3D0)>): Higher is better; unit: PERCENT.

- [Pu (R=1%)](<https://www.sota2.com/research/sota/watermark-detection-on-ffhq.md?metric=Pu%20(R%3D1%25)>): Higher is better; unit: PERCENT.

- [Pu (R=5%)](<https://www.sota2.com/research/sota/watermark-detection-on-ffhq.md?metric=Pu%20(R%3D5%25)>): Higher is better; unit: PERCENT.

- [Pu (R=10%)](<https://www.sota2.com/research/sota/watermark-detection-on-ffhq.md?metric=Pu%20(R%3D10%25)>): Higher is better; unit: PERCENT.

- [Pu (R=20%)](<https://www.sota2.com/research/sota/watermark-detection-on-ffhq.md?metric=Pu%20(R%3D20%25)>): Higher is better; unit: PERCENT.

- [Pu (R=50%)](<https://www.sota2.com/research/sota/watermark-detection-on-ffhq.md?metric=Pu%20(R%3D50%25)>): Higher is better; unit: PERCENT.

- [Pu (R=100%)](<https://www.sota2.com/research/sota/watermark-detection-on-ffhq.md?metric=Pu%20(R%3D100%25)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Pu (R=0) | Result date | Report paper |
| --- | --- | --- | --- |
| DIAGNOSIS | 3.8 | Not recorded | 68fa77721e209131cea73257 |
| CoprGuard | 0 | Not recorded | 68fa77721e209131cea73257 |

### DIAGNOSIS

Pu (R=0): 3.8. Result ID: 69949e463a6c3148491e71f9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77721e209131cea73257.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72ce1e209131cea589b2.md>)

Recorded evaluation configuration: {"Model":"DDIM"}. This record does not assert independent reproduction.

### CoprGuard

Pu (R=0): 0. Result ID: 69949e463a6c3148491e71fa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77721e209131cea73257.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77721e209131cea73257.md>)

[Implementation](<https://github.com/sccsok/CoprGuard.git>)

Recorded evaluation configuration: {"Model":"DDIM"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.