# Image Classification on CIFAR-100 (Adversarial Robustness Evaluation)

Source: [Image Classification on CIFAR-100 (Adversarial Robustness Evaluation)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-adversarial-robustness-evaluation>)

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

Data updated: 2026-03-10T10:04:21.151Z

Evaluation of Image Classification performance on the CIFAR-100 dataset, reporting accuracy under various specific adversarial attack scenarios (FGSM, AGSM, PGD, PAGD) alongside clean accuracy.

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 Classification |
| Dataset (including any stated split) | CIFAR-100 |
| Metric | FGSM Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [FGSM Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-adversarial-robustness-evaluation.md?metric=FGSM%20Accuracy>): Higher is better; unit: PERCENT.

- [AGSM Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-adversarial-robustness-evaluation.md?metric=AGSM%20Accuracy>): Higher is better; unit: PERCENT.

- [PGD Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-adversarial-robustness-evaluation.md?metric=PGD%20Accuracy>): Higher is better; unit: PERCENT.

- [PAGD Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-adversarial-robustness-evaluation.md?metric=PAGD%20Accuracy>): Higher is better; unit: PERCENT.

- [Clean Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-adversarial-robustness-evaluation.md?metric=Clean%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | FGSM Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Poincare ResNet-32 | 26.36 | Not recorded | 691bfe1a6750be83fe5cecb2 |
| Poincare ResNet-20 | 24.67 | Not recorded | 691bfe1a6750be83fe5cecb2 |
| Poincare ResNet-32 | 24.61 | Not recorded | 691bfe1a6750be83fe5cecb2 |
| Poincare ResNet-20 | 22.62 | Not recorded | 691bfe1a6750be83fe5cecb2 |
| Poincare ResNet-32 | 19.67 | Not recorded | 691bfe1a6750be83fe5cecb2 |
| Poincare ResNet-20 | 17.78 | Not recorded | 691bfe1a6750be83fe5cecb2 |

### Poincare ResNet-32

FGSM Accuracy: 26.36. Result ID: 69afec9a6dbb7075b958d323.

[Reporting paper](<https://www.sota2.com/research/paper/691bfe1a6750be83fe5cecb2.md>)

Recorded evaluation configuration: {"Model":"PRN 32","ε":"2.4/255 (ε1)"}. This record does not assert independent reproduction.

### Poincare ResNet-20

FGSM Accuracy: 24.67. Result ID: 69afec9a6dbb7075b958d320.

[Reporting paper](<https://www.sota2.com/research/paper/691bfe1a6750be83fe5cecb2.md>)

Recorded evaluation configuration: {"Model":"PRN 20","ε":"2.4/255 (ε1)"}. This record does not assert independent reproduction.

### Poincare ResNet-32

FGSM Accuracy: 24.61. Result ID: 69afec9a6dbb7075b958d324.

[Reporting paper](<https://www.sota2.com/research/paper/691bfe1a6750be83fe5cecb2.md>)

Recorded evaluation configuration: {"Model":"PRN 32","ε":"3.2/255 (ε2)"}. This record does not assert independent reproduction.

### Poincare ResNet-20

FGSM Accuracy: 22.62. Result ID: 69afec9a6dbb7075b958d321.

[Reporting paper](<https://www.sota2.com/research/paper/691bfe1a6750be83fe5cecb2.md>)

Recorded evaluation configuration: {"Model":"PRN 20","ε":"3.2/255 (ε2)"}. This record does not assert independent reproduction.

### Poincare ResNet-32

FGSM Accuracy: 19.67. Result ID: 69afec9a6dbb7075b958d325.

[Reporting paper](<https://www.sota2.com/research/paper/691bfe1a6750be83fe5cecb2.md>)

Recorded evaluation configuration: {"Model":"PRN 32","ε":"8.0/255 (ε3)"}. This record does not assert independent reproduction.

### Poincare ResNet-20

FGSM Accuracy: 17.78. Result ID: 69afec9a6dbb7075b958d322.

[Reporting paper](<https://www.sota2.com/research/paper/691bfe1a6750be83fe5cecb2.md>)

Recorded evaluation configuration: {"Model":"PRN 20","ε":"8.0/255 (ε3)"}. This record does not assert independent reproduction.

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