# Robustness Evaluation on CIFAR10

Source: [Robustness Evaluation on CIFAR10](<https://www.sota2.com/research/sota/robustness-evaluation-on-cifar10>)

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

Data updated: 2026-06-04T12:49:59.289Z

Evaluation of model robustness on the CIFAR-10 dataset using specific adversarial robustness metrics such as L(x), CLEVER, CW, PGD, Rnorm, and Rspec.

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 | Robustness Evaluation |
| Dataset (including any stated split) | CIFAR10 |
| Metric | L(x) |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| 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

- [L(x)](<https://www.sota2.com/research/sota/robustness-evaluation-on-cifar10.md?metric=L(x)>): Higher is better; unit: SCALAR.

- [CLEVER Score](<https://www.sota2.com/research/sota/robustness-evaluation-on-cifar10.md?metric=CLEVER%20Score>): Higher is better; unit: SCALAR.

- [CW Score](<https://www.sota2.com/research/sota/robustness-evaluation-on-cifar10.md?metric=CW%20Score>): Higher is better; unit: SCALAR.

- [PGD Robust Accuracy](<https://www.sota2.com/research/sota/robustness-evaluation-on-cifar10.md?metric=PGD%20Robust%20Accuracy>): Higher is better; unit: PERCENT.

- [Rnorm Score](<https://www.sota2.com/research/sota/robustness-evaluation-on-cifar10.md?metric=Rnorm%20Score>): Higher is better; unit: SCALAR.

- [Rspec Score](<https://www.sota2.com/research/sota/robustness-evaluation-on-cifar10.md?metric=Rspec%20Score>): Higher is better; unit: SCALAR.

## Recorded results

| Method | L(x) | Result date | Report paper |
| --- | --- | --- | --- |
| DenseNet121 | 0.47 | Not recorded | 6a210703c10484bac23f07e7 |
| ResNet18 | 0.29 | Not recorded | 6a210703c10484bac23f07e7 |
| ViT B 16 | 0.25 | Not recorded | 6a210703c10484bac23f07e7 |
| VGG16 | 0.07 | Not recorded | 6a210703c10484bac23f07e7 |

### DenseNet121

L(x): 0.47. Result ID: 6a2173f0fbc373592c1eb1a2.

[Reporting paper](<https://www.sota2.com/research/paper/6a210703c10484bac23f07e7.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### ResNet18

L(x): 0.29. Result ID: 6a2173f0fbc373592c1eb1a3.

[Reporting paper](<https://www.sota2.com/research/paper/6a210703c10484bac23f07e7.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### ViT B 16

L(x): 0.25. Result ID: 6a2173f0fbc373592c1eb1a4.

[Reporting paper](<https://www.sota2.com/research/paper/6a210703c10484bac23f07e7.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa703d1e209131cea49db1.md>)

[Implementation](<https://github.com/tensorflow/tensor2tensor>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### VGG16

L(x): 0.07. Result ID: 6a2173f0fbc373592c1eb1a5.

[Reporting paper](<https://www.sota2.com/research/paper/6a210703c10484bac23f07e7.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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