# Facial Attribute Editing Defense on Attention GAN (test)

Source: [Facial Attribute Editing Defense on Attention GAN (test)](<https://www.sota2.com/research/sota/facial-attribute-editing-defense-on-attention-gan-test>)

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

Data updated: 2026-04-03T07:54:53.685Z

Evaluation of a defense mechanism against facial attribute editing attacks using the Attention GAN test set, measured by fidelity metrics (PSNR, SSIM, LPIPS) and identity preservation (DSR).

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 | Facial Attribute Editing Defense |
| Dataset (including any stated split) | Attention GAN (test) |
| Metric | PSNR |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| 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

- [PSNR](<https://www.sota2.com/research/sota/facial-attribute-editing-defense-on-attention-gan-test.md?metric=PSNR>): Higher is better; unit: SCALAR.

- [SSIM](<https://www.sota2.com/research/sota/facial-attribute-editing-defense-on-attention-gan-test.md?metric=SSIM>): Higher is better; unit: PERCENT.

- [LPIPS](<https://www.sota2.com/research/sota/facial-attribute-editing-defense-on-attention-gan-test.md?metric=LPIPS>): Lower is better; unit: SCALAR.

- [DSR](<https://www.sota2.com/research/sota/facial-attribute-editing-defense-on-attention-gan-test.md?metric=DSR>): Higher is better; unit: PERCENT.

## Recorded results

| Method | PSNR | Result date | Report paper |
| --- | --- | --- | --- |
| RUIP | 41.416 | Not recorded | 69cf497b0636e5bf4afcd9bf |
| Venom | 33.335 | Not recorded | 69cf497b0636e5bf4afcd9bf |
| AEGIS | 30.202 | Not recorded | 69cf497b0636e5bf4afcd9bf |

### RUIP

PSNR: 41.416. Result ID: 69cf723647f34ce924b914ed.

[Reporting paper](<https://www.sota2.com/research/paper/69cf497b0636e5bf4afcd9bf.md>)

Recorded evaluation configuration: {"Setting":"Black-box setting"}. This record does not assert independent reproduction.

### Venom

PSNR: 33.335. Result ID: 69cf723647f34ce924b914ec.

[Reporting paper](<https://www.sota2.com/research/paper/69cf497b0636e5bf4afcd9bf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b7f1e209131cea2e9ce.md>)

Recorded evaluation configuration: {"Setting":"Black-box setting"}. This record does not assert independent reproduction.

### AEGIS

PSNR: 30.202. Result ID: 69cf723647f34ce924b914ee.

[Reporting paper](<https://www.sota2.com/research/paper/69cf497b0636e5bf4afcd9bf.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69cf497b0636e5bf4afcd9bf.md>)

Recorded evaluation configuration: {"Setting":"Black-box setting"}. This record does not assert independent reproduction.

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