# Image Classification on CIFAR10 (Accuracy, ∆CA, ASR Tracking)

Source: [Image Classification on CIFAR10 (Accuracy, ∆CA, ASR Tracking)](<https://www.sota2.com/research/sota/image-classification-on-cifar10-accuracy-ca-asr-tracking>)

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

Data updated: 2026-02-26T06:11:26.151Z

Evaluation of Image Classification performance on the CIFAR-10 dataset, reporting standard Accuracy alongside change analysis metrics (∆CA) and Attack Success Rate (ASR).

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) | CIFAR10 |
| Metric | ∆CA |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [∆CA](<https://www.sota2.com/research/sota/image-classification-on-cifar10-accuracy-ca-asr-tracking.md?metric=%E2%88%86CA>): Higher is better; unit: SCALAR.

- [Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar10-accuracy-ca-asr-tracking.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [ASR](<https://www.sota2.com/research/sota/image-classification-on-cifar10-accuracy-ca-asr-tracking.md?metric=ASR>): Lower is better; unit: PERCENT.

## Recorded results

| Method | ∆CA | Result date | Report paper |
| --- | --- | --- | --- |
| PRISM | 2.3 | Not recorded | 69799847a2b28e761d87ccd6 |
| PRISM | 0.6 | Not recorded | 69799847a2b28e761d87ccd6 |
| PRISM | 0.5 | Not recorded | 69799847a2b28e761d87ccd6 |

### PRISM

∆CA: 2.3. Result ID: 69990ecc5698665ec474964e.

[Reporting paper](<https://www.sota2.com/research/paper/69799847a2b28e761d87ccd6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69799847a2b28e761d87ccd6.md>)

Recorded evaluation configuration: {"IR":1,"Attack Type":"BPP","Backbone":"ResNet-50"}. This record does not assert independent reproduction.

### PRISM

∆CA: 0.6. Result ID: 69990ecc5698665ec474964f.

[Reporting paper](<https://www.sota2.com/research/paper/69799847a2b28e761d87ccd6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69799847a2b28e761d87ccd6.md>)

Recorded evaluation configuration: {"IR":1,"Attack Type":"CTRL","Backbone":"ResNet-50"}. This record does not assert independent reproduction.

### PRISM

∆CA: 0.5. Result ID: 69990ecc5698665ec474964d.

[Reporting paper](<https://www.sota2.com/research/paper/69799847a2b28e761d87ccd6.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69799847a2b28e761d87ccd6.md>)

Recorded evaluation configuration: {"IR":1,"Attack Type":"Blend","Backbone":"ResNet-50"}. This record does not assert independent reproduction.

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