# Image Classification on MNIST (test) (ASR and Robustness Metrics)

Source: [Image Classification on MNIST (test) (ASR and Robustness Metrics)](<https://www.sota2.com/research/sota/image-classification-on-mnist-test-asr-and-robustness-metrics>)

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

Data updated: 2026-02-26T05:23:57.606Z

Evaluation of Image Classification performance on the MNIST test set, reporting metrics related to adversarial robustness, including Attack Success Rate (ASR), Robust Accuracy, and Accuracy Gap.

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) | MNIST (test) |
| Metric | ASR |
| Unit | PERCENT |
| Direction | Lower 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

- [ASR](<https://www.sota2.com/research/sota/image-classification-on-mnist-test-asr-and-robustness-metrics.md?metric=ASR>): Lower is better; unit: PERCENT.

- [Robust Accuracy](<https://www.sota2.com/research/sota/image-classification-on-mnist-test-asr-and-robustness-metrics.md?metric=Robust%20Accuracy>): Higher is better; unit: PERCENT.

- [Accuracy Gap](<https://www.sota2.com/research/sota/image-classification-on-mnist-test-asr-and-robustness-metrics.md?metric=Accuracy%20Gap>): Lower is better; unit: PERCENT.

## Recorded results

| Method | ASR | Result date | Report paper |
| --- | --- | --- | --- |
| RIFLE | 12 | Not recorded | 698abbe1c97a0b3e3b5de2a4 |
| FedBary | 14 | Not recorded | 698abbe1c97a0b3e3b5de2a4 |
| PyramidFL | 80 | Not recorded | 698abbe1c97a0b3e3b5de2a4 |
| FedGA | 83 | Not recorded | 698abbe1c97a0b3e3b5de2a4 |

### RIFLE

ASR: 12. Result ID: 6998d9165698665ec43d0536.

[Reporting paper](<https://www.sota2.com/research/paper/698abbe1c97a0b3e3b5de2a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/698abbe1c97a0b3e3b5de2a4.md>)

Recorded evaluation configuration: {"Adversarial Condition":"Model Poisoning"}. This record does not assert independent reproduction.

### FedBary

ASR: 14. Result ID: 6998d9165698665ec43d0535.

[Reporting paper](<https://www.sota2.com/research/paper/698abbe1c97a0b3e3b5de2a4.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa732c1e209131cea5aefb.md>)

Recorded evaluation configuration: {"Adversarial Condition":"Model Poisoning"}. This record does not assert independent reproduction.

### PyramidFL

ASR: 80. Result ID: 6998d9165698665ec43d0534.

[Reporting paper](<https://www.sota2.com/research/paper/698abbe1c97a0b3e3b5de2a4.md>)

Recorded evaluation configuration: {"Adversarial Condition":"Model Poisoning"}. This record does not assert independent reproduction.

### FedGA

ASR: 83. Result ID: 6998d9165698665ec43d0533.

[Reporting paper](<https://www.sota2.com/research/paper/698abbe1c97a0b3e3b5de2a4.md>)

Recorded evaluation configuration: {"Adversarial Condition":"Model Poisoning"}. This record does not assert independent reproduction.

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