# Image-level forgery detection on Flux Kontext

Source: [Image-level forgery detection on Flux Kontext](<https://www.sota2.com/research/sota/image-level-forgery-detection-on-flux-kontext>)

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

Data updated: 2026-06-02T12:58:07.658Z

Evaluation of Image-level forgery detection performance on the Flux Kontext dataset, reporting ACC and AP.

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 | Image-level forgery detection |
| Dataset (including any stated split) | Flux Kontext |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/image-level-forgery-detection-on-flux-kontext.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Average Precision](<https://www.sota2.com/research/sota/image-level-forgery-detection-on-flux-kontext.md?metric=Average%20Precision>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| FLAME-F† | 79.2 | Not recorded | 6a1e641adbd7150506f85710 |
| FLAME | 75.4 | Not recorded | 6a1e641adbd7150506f85710 |
| SAFIRE | 61.6 | Not recorded | 6a1e641adbd7150506f85710 |
| TruFor | 57.8 | Not recorded | 6a1e641adbd7150506f85710 |
| Mesorch | 54.7 | Not recorded | 6a1e641adbd7150506f85710 |
| AdaIFL | 52.3 | Not recorded | 6a1e641adbd7150506f85710 |
| SIDA | 52.2 | Not recorded | 6a1e641adbd7150506f85710 |
| FakeShield | 49.3 | Not recorded | 6a1e641adbd7150506f85710 |
| SparseViT | 49 | Not recorded | 6a1e641adbd7150506f85710 |

### FLAME-F†

Accuracy: 79.2. Result ID: 6a1ed348fbc373592c1ab589.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e641adbd7150506f85710.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a1e641adbd7150506f85710.md>)

Recorded evaluation configuration: {"Evaluation Setting":"Fine-tuned","Fine-tuning Pipeline":"EditStream"}. This record does not assert independent reproduction.

### FLAME

Accuracy: 75.4. Result ID: 6a1ed348fbc373592c1ab588.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e641adbd7150506f85710.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a1e641adbd7150506f85710.md>)

Recorded evaluation configuration: {"Evaluation Setting":"Zero-shot","Model Version":"Base"}. This record does not assert independent reproduction.

### SAFIRE

Accuracy: 61.6. Result ID: 6a1ed348fbc373592c1ab581.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e641adbd7150506f85710.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76201e209131cea6b5cc.md>)

Recorded evaluation configuration: {"Evaluation Setting":"Zero-shot"}. This record does not assert independent reproduction.

### TruFor

Accuracy: 57.8. Result ID: 6a1ed348fbc373592c1ab583.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e641adbd7150506f85710.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f7f1e209131cea45fb0.md>)

[Implementation](<https://grip-unina.github.io/TruFor/>)

Recorded evaluation configuration: {"Evaluation Setting":"Zero-shot"}. This record does not assert independent reproduction.

### Mesorch

Accuracy: 54.7. Result ID: 6a1ed348fbc373592c1ab582.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e641adbd7150506f85710.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76511e209131cea6c606.md>)

[Implementation](<https://github.com/scu-zjz/Mesorch>)

Recorded evaluation configuration: {"Evaluation Setting":"Zero-shot"}. This record does not assert independent reproduction.

### AdaIFL

Accuracy: 52.3. Result ID: 6a1ed348fbc373592c1ab584.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e641adbd7150506f85710.md>)

Recorded evaluation configuration: {"Evaluation Setting":"Zero-shot"}. This record does not assert independent reproduction.

### SIDA

Accuracy: 52.2. Result ID: 6a1ed348fbc373592c1ab585.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e641adbd7150506f85710.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa79a11e209131cea7e8bc.md>)

[Implementation](<https://hzlsaber.github.io/projects/SIDA/>)

Recorded evaluation configuration: {"Evaluation Setting":"Zero-shot"}. This record does not assert independent reproduction.

### FakeShield

Accuracy: 49.3. Result ID: 6a1ed348fbc373592c1ab586.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e641adbd7150506f85710.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77ea1e209131cea75f70.md>)

Recorded evaluation configuration: {"Evaluation Setting":"Zero-shot"}. This record does not assert independent reproduction.

### SparseViT

Accuracy: 49. Result ID: 6a1ed348fbc373592c1ab587.

[Reporting paper](<https://www.sota2.com/research/paper/6a1e641adbd7150506f85710.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa765b1e209131cea6c95b.md>)

Recorded evaluation configuration: {"Evaluation Setting":"Zero-shot"}. This record does not assert independent reproduction.

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