# Watermark Extraction on SD 3.5

Source: [Watermark Extraction on SD 3.5](<https://www.sota2.com/research/sota/watermark-extraction-on-sd-3-5>)

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

Data updated: 2026-02-26T05:39:21.415Z

Evaluation of Watermark Extraction performance on the SD 3.5 dataset, reporting metrics such as Clean Bit Accuracy, Adversarial Bit Accuracy, and Payload Rate.

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 Extraction |
| Dataset (including any stated split) | SD 3.5 |
| Metric | Clean Bit Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [Clean Bit Accuracy](<https://www.sota2.com/research/sota/watermark-extraction-on-sd-3-5.md?metric=Clean%20Bit%20Accuracy>): Higher is better; unit: PERCENT.

- [Adversarial Bit Accuracy](<https://www.sota2.com/research/sota/watermark-extraction-on-sd-3-5.md?metric=Adversarial%20Bit%20Accuracy>): Higher is better; unit: PERCENT.

- [Payload Rate](<https://www.sota2.com/research/sota/watermark-extraction-on-sd-3-5.md?metric=Payload%20Rate>): Higher is better; unit: PERCENT.

- [FLOPs (T)](<https://www.sota2.com/research/sota/watermark-extraction-on-sd-3-5.md?metric=FLOPs%20(T)>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Clean Bit Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| OSI | 99.93 | Not recorded | 698c0d4cc97a0b3e3b5e1304 |
| GS | 99.82 | Not recorded | 698c0d4cc97a0b3e3b5e1304 |
| OSI | 98.58 | Not recorded | 698c0d4cc97a0b3e3b5e1304 |
| GS | 97.46 | Not recorded | 698c0d4cc97a0b3e3b5e1304 |
| OSI | 88.87 | Not recorded | 698c0d4cc97a0b3e3b5e1304 |
| GS | 85.2 | Not recorded | 698c0d4cc97a0b3e3b5e1304 |
| OSI | 79.78 | Not recorded | 698c0d4cc97a0b3e3b5e1304 |
| GS | 76.04 | Not recorded | 698c0d4cc97a0b3e3b5e1304 |

### OSI

Clean Bit Accuracy: 99.93. Result ID: 69971f7e5698665ec46da96c.

[Reporting paper](<https://www.sota2.com/research/paper/698c0d4cc97a0b3e3b5e1304.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698c0d4cc97a0b3e3b5e1304.md>)

Recorded evaluation configuration: {"f\_hw":"8"}. This record does not assert independent reproduction.

### GS

Clean Bit Accuracy: 99.82. Result ID: 69971f7e5698665ec46da968.

[Reporting paper](<https://www.sota2.com/research/paper/698c0d4cc97a0b3e3b5e1304.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73131e209131cea5a4a6.md>)

Recorded evaluation configuration: {"f\_hw":"8"}. This record does not assert independent reproduction.

### OSI

Clean Bit Accuracy: 98.58. Result ID: 69971f7e5698665ec46da96b.

[Reporting paper](<https://www.sota2.com/research/paper/698c0d4cc97a0b3e3b5e1304.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698c0d4cc97a0b3e3b5e1304.md>)

Recorded evaluation configuration: {"f\_hw":"4"}. This record does not assert independent reproduction.

### GS

Clean Bit Accuracy: 97.46. Result ID: 69971f7e5698665ec46da967.

[Reporting paper](<https://www.sota2.com/research/paper/698c0d4cc97a0b3e3b5e1304.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73131e209131cea5a4a6.md>)

Recorded evaluation configuration: {"f\_hw":"4"}. This record does not assert independent reproduction.

### OSI

Clean Bit Accuracy: 88.87. Result ID: 69971f7e5698665ec46da96a.

[Reporting paper](<https://www.sota2.com/research/paper/698c0d4cc97a0b3e3b5e1304.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698c0d4cc97a0b3e3b5e1304.md>)

Recorded evaluation configuration: {"f\_hw":"2"}. This record does not assert independent reproduction.

### GS

Clean Bit Accuracy: 85.2. Result ID: 69971f7e5698665ec46da966.

[Reporting paper](<https://www.sota2.com/research/paper/698c0d4cc97a0b3e3b5e1304.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73131e209131cea5a4a6.md>)

Recorded evaluation configuration: {"f\_hw":"2"}. This record does not assert independent reproduction.

### OSI

Clean Bit Accuracy: 79.78. Result ID: 69971f7e5698665ec46da969.

[Reporting paper](<https://www.sota2.com/research/paper/698c0d4cc97a0b3e3b5e1304.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698c0d4cc97a0b3e3b5e1304.md>)

Recorded evaluation configuration: {"f\_hw":"1"}. This record does not assert independent reproduction.

### GS

Clean Bit Accuracy: 76.04. Result ID: 69971f7e5698665ec46da965.

[Reporting paper](<https://www.sota2.com/research/paper/698c0d4cc97a0b3e3b5e1304.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa73131e209131cea5a4a6.md>)

Recorded evaluation configuration: {"f\_hw":"1"}. This record does not assert independent reproduction.

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