# Zero-shot Image Classification on Aircraft (Adversarial Robustness Metrics)

Source: [Zero-shot Image Classification on Aircraft (Adversarial Robustness Metrics)](<https://www.sota2.com/research/sota/zero-shot-image-classification-on-aircraft-adversarial-robustness-metrics>)

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

Data updated: 2026-05-19T11:02:25.122Z

Evaluation of Zero-shot Image Classification performance on the Aircraft dataset, specifically measuring robustness against adversarial attacks using PGD, CW, DI, and AA metrics.

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 | Zero-shot Image Classification |
| Dataset (including any stated split) | Aircraft |
| Metric | PGD Error |
| Unit | PERCENT |
| Direction | Lower 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

- [PGD Error](<https://www.sota2.com/research/sota/zero-shot-image-classification-on-aircraft-adversarial-robustness-metrics.md?metric=PGD%20Error>): Lower is better; unit: PERCENT.

- [CW Error](<https://www.sota2.com/research/sota/zero-shot-image-classification-on-aircraft-adversarial-robustness-metrics.md?metric=CW%20Error>): Lower is better; unit: PERCENT.

- [DI Error](<https://www.sota2.com/research/sota/zero-shot-image-classification-on-aircraft-adversarial-robustness-metrics.md?metric=DI%20Error>): Lower is better; unit: PERCENT.

- [AA Error](<https://www.sota2.com/research/sota/zero-shot-image-classification-on-aircraft-adversarial-robustness-metrics.md?metric=AA%20Error>): Lower is better; unit: PERCENT.

## Recorded results

| Method | PGD Error | Result date | Report paper |
| --- | --- | --- | --- |
| Vanilla | 0 | Not recorded | 6a0beee6dbc836b87d82c7fb |
| TAME | 8.4 | Not recorded | 6a0beee6dbc836b87d82c7fb |

### Vanilla

PGD Error: 0. Result ID: 6a0c4251fbc373592c032bd2.

[Reporting paper](<https://www.sota2.com/research/paper/6a0beee6dbc836b87d82c7fb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69581e209131cea21ad0.md>)

[Implementation](<https://github.com/OpenAI/CLIP>)

Recorded evaluation configuration: {"Backbone":"ViT-B/32","Evaluation Protocol":"Zero-shot"}. This record does not assert independent reproduction.

### TAME

PGD Error: 8.4. Result ID: 6a0c4251fbc373592c032bd3.

[Reporting paper](<https://www.sota2.com/research/paper/6a0beee6dbc836b87d82c7fb.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0beee6dbc836b87d82c7fb.md>)

Recorded evaluation configuration: {"Backbone":"ViT-B/32","Evaluation Protocol":"Zero-shot","Prompt Configuration":"V-L Independent"}. This record does not assert independent reproduction.

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