# Image Classification on CIFAR-10 all-to-all setting, SIG attack (test)

Source: [Image Classification on CIFAR-10 all-to-all setting, SIG attack (test)](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-all-to-all-setting-sig-attack-test>)

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

Data updated: 2026-02-26T05:28:39.101Z

Evaluation of Image Classification performance on the CIFAR-10 dataset under a SIG adversarial attack scenario, tested in an all-to-all setting.

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 all-to-all setting, SIG attack (test) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 8 of 8 |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-all-to-all-setting-sig-attack-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Attack Success Rate](<https://www.sota2.com/research/sota/image-classification-on-cifar-10-all-to-all-setting-sig-attack-test.md?metric=Attack%20Success%20Rate>): Lower is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Before | 94.66 | Not recorded | 68fa6e481e209131cea3ef5e |
| Neural Cleanse | 94.66 | Not recorded | 68fa6e481e209131cea3ef5e |
| PBE | 93.71 | Not recorded | 68fa6e481e209131cea3ef5e |
| ANP | 93.6 | Not recorded | 68fa6e481e209131cea3ef5e |
| PBE | 93.52 | Not recorded | 68fa6e481e209131cea3ef5e |
| NAD | 91.53 | Not recorded | 68fa6e481e209131cea3ef5e |
| Fine-pruning | 88.99 | Not recorded | 68fa6e481e209131cea3ef5e |
| Fine-tuning | 87.98 | Not recorded | 68fa6e481e209131cea3ef5e |

### Before

Accuracy: 94.66. Result ID: 69900c553a6c314849fdbe29.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e481e209131cea3ef5e.md>)

Recorded evaluation configuration: {"defense":"None"}. This record does not assert independent reproduction.

### Neural Cleanse

Accuracy: 94.66. Result ID: 69900c553a6c314849fdbe2d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e481e209131cea3ef5e.md>)

Recorded evaluation configuration: {"defense":"Neural Cleanse"}. This record does not assert independent reproduction.

### PBE

Accuracy: 93.71. Result ID: 69900c553a6c314849fdbe2f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e481e209131cea3ef5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e481e209131cea3ef5e.md>)

Recorded evaluation configuration: {"clean\_data\_available":false}. This record does not assert independent reproduction.

### ANP

Accuracy: 93.6. Result ID: 69900c553a6c314849fdbe2e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e481e209131cea3ef5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6b181e209131cea2c1a4.md>)

[Implementation](<https://github.com/csdongxian/ANP_backdoor>)

Recorded evaluation configuration: {"defense":"Adversarial Neuron Pruning"}. This record does not assert independent reproduction.

### PBE

Accuracy: 93.52. Result ID: 69900c553a6c314849fdbe30.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e481e209131cea3ef5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6e481e209131cea3ef5e.md>)

Recorded evaluation configuration: {"clean\_data\_available":true}. This record does not assert independent reproduction.

### NAD

Accuracy: 91.53. Result ID: 69900c553a6c314849fdbe2c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e481e209131cea3ef5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69321e209131cea20c09.md>)

Recorded evaluation configuration: {"defense":"Neural Attention Distillation"}. This record does not assert independent reproduction.

### Fine-pruning

Accuracy: 88.99. Result ID: 69900c553a6c314849fdbe2b.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e481e209131cea3ef5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa646b1e209131cea04983.md>)

Recorded evaluation configuration: {"defense":"Fine-pruning"}. This record does not assert independent reproduction.

### Fine-tuning

Accuracy: 87.98. Result ID: 69900c553a6c314849fdbe2a.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6e481e209131cea3ef5e.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7aa21e209131cea84435.md>)

Recorded evaluation configuration: {"defense":"Fine-tuning"}. This record does not assert independent reproduction.

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