# Image Classification on CIFAR-10 (test) (Epsilon-Specific Accuracy: 1, 2, 4, 8)

Source: [Image Classification on CIFAR-10 (test) (Epsilon-Specific Accuracy: 1, 2, 4, 8)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-epsilon-specific-accuracy-1-2-4-8>)

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

Data updated: 2026-02-26T06:07:16.280Z

Evaluation of Image Classification performance on the CIFAR-10 test set using Top-1 Accuracy measured under specific epsilon constraints (ε=1, 2, 4, and 8), likely related to robustness or calibration testing.

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-10 (test) |
| Metric | Top-1 Accuracy (eps=1) |
| Unit | PERCENT |
| Direction | Higher 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

- [Top-1 Accuracy (eps=1)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-epsilon-specific-accuracy-1-2-4-8.md?metric=Top-1%20Accuracy%20(eps%3D1)>): Higher is better; unit: PERCENT.

- [Top-1 Accuracy (eps=2)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-epsilon-specific-accuracy-1-2-4-8.md?metric=Top-1%20Accuracy%20(eps%3D2)>): Higher is better; unit: PERCENT.

- [Top-1 Accuracy (eps=4)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-epsilon-specific-accuracy-1-2-4-8.md?metric=Top-1%20Accuracy%20(eps%3D4)>): Higher is better; unit: PERCENT.

- [Top-1 Accuracy (eps=8)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-test-epsilon-specific-accuracy-1-2-4-8.md?metric=Top-1%20Accuracy%20(eps%3D8)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Top-1 Accuracy (eps=1) | Result date | Report paper |
| --- | --- | --- | --- |
| DP-SGD | 94.7 | Not recorded | 68fa6cbf1e209131cea35c41 |
| DP-SGD | 56.8 | Not recorded | 68fa6cbf1e209131cea35c41 |

### DP-SGD

Top-1 Accuracy (eps=1): 94.7. Result ID: 698f3afb3a6c314849f74cfd.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cbf1e209131cea35c41.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cbf1e209131cea35c41.md>)

[Implementation](<https://github.com/deepmind/jax_privacy>)

Recorded evaluation configuration: {"Pre-Training Data":"ImageNet","Architecture":"Wide-ResNets","delta":"10^-5"}. This record does not assert independent reproduction.

### DP-SGD

Top-1 Accuracy (eps=1): 56.8. Result ID: 698f3afb3a6c314849f74cfc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6cbf1e209131cea35c41.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6cbf1e209131cea35c41.md>)

[Implementation](<https://github.com/deepmind/jax_privacy>)

Recorded evaluation configuration: {"Pre-Training Data":"None","Architecture":"Wide-ResNets","delta":"10^-5"}. This record does not assert independent reproduction.

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