# Adversarial Attack on Text-to-Image Generation on ImageNet Long Prompt 1K (val)

Source: [Adversarial Attack on Text-to-Image Generation on ImageNet Long Prompt 1K (val)](<https://www.sota2.com/research/sota/adversarial-attack-on-text-to-image-generation-on-imagenet-long-prompt-1k-val>)

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

Data updated: 2026-02-26T05:44:23.356Z

Evaluation of adversarial attack performance targeting Text-to-Image generation models using the ImageNet Long Prompt 1K validation set. Metrics focus on generation quality (FID, IS, TS) and attack success 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 | Adversarial Attack on Text-to-Image Generation |
| Dataset (including any stated split) | ImageNet Long Prompt 1K (val) |
| Metric | FID |
| Unit | SCALAR |
| Direction | Lower 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

- [FID](<https://www.sota2.com/research/sota/adversarial-attack-on-text-to-image-generation-on-imagenet-long-prompt-1k-val.md?metric=FID>): Lower is better; unit: SCALAR.

- [Attack Success Rate](<https://www.sota2.com/research/sota/adversarial-attack-on-text-to-image-generation-on-imagenet-long-prompt-1k-val.md?metric=Attack%20Success%20Rate>): Higher is better; unit: PERCENT.

- [IS](<https://www.sota2.com/research/sota/adversarial-attack-on-text-to-image-generation-on-imagenet-long-prompt-1k-val.md?metric=IS>): Higher is better; unit: SCALAR.

- [TS](<https://www.sota2.com/research/sota/adversarial-attack-on-text-to-image-generation-on-imagenet-long-prompt-1k-val.md?metric=TS>): Higher is better; unit: SCALAR.

## Recorded results

| Method | FID | Result date | Report paper |
| --- | --- | --- | --- |
| Clean | 17.95 | Not recorded | 68fa6fa21e209131cea46d08 |
| Random | 24.16 | Not recorded | 68fa6fa21e209131cea46d08 |
| ATM | 29.65 | Not recorded | 68fa6fa21e209131cea46d08 |

### Clean

FID: 17.95. Result ID: 6990f8163a6c31484904afec.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fa21e209131cea46d08.md>)

Recorded evaluation configuration: {"Prompt Type":"Long"}. This record does not assert independent reproduction.

### Random

FID: 24.16. Result ID: 6990f8163a6c31484904afed.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fa21e209131cea46d08.md>)

Recorded evaluation configuration: {"Prompt Type":"Long"}. This record does not assert independent reproduction.

### ATM

FID: 29.65. Result ID: 6990f8163a6c31484904afee.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6fa21e209131cea46d08.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6fa21e209131cea46d08.md>)

Recorded evaluation configuration: {"Prompt Type":"Long","Search iterations":100,"Learning rate":0.3,"Margin":30}. This record does not assert independent reproduction.

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