# Image Classification on CIFAR-100 (Average Robust Accuracy)

Source: [Image Classification on CIFAR-100 (Average Robust Accuracy)](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-average-robust-accuracy>)

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

Data updated: 2026-04-07T09:42:43.396Z

Evaluation of Image Classification performance on the CIFAR-100 dataset, specifically reporting the Average Robust Accuracy metric.

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-100 |
| Metric | Average Robust Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 15 of 15 |
| 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

- [Average Robust Accuracy](<https://www.sota2.com/research/sota/image-classification-on-cifar-100-average-robust-accuracy.md?metric=Average%20Robust%20Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Average Robust Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| ATAC | 86.27 | Not recorded | 6923e676d6b0dd334292eee0 |
| Comp-TGA | 19.36 | Not recorded | 69bcd4780636e5bf4afc2992 |
| TGA-ZSR | 14.43 | Not recorded | 69bcd4780636e5bf4afc2992 |
| PMG-AFT | 13.29 | Not recorded | 69bcd4780636e5bf4afc2992 |
| LAAT | 12.87 | Not recorded | 69bcd4780636e5bf4afc2992 |
| ATAC | 11.25 | Not recorded | 6923e676d6b0dd334292eee0 |
| FT-Adv. | 11.06 | Not recorded | 69bcd4780636e5bf4afc2992 |
| TTC | 9.06 | Not recorded | 6923e676d6b0dd334292eee0 |
| TeCoA | 8.12 | Not recorded | 69bcd4780636e5bf4afc2992 |
| ATAC | 5.83 | Not recorded | 6923e676d6b0dd334292eee0 |
| FT-Clean | 4.65 | Not recorded | 69bcd4780636e5bf4afc2992 |
| FARE | 4.23 | Not recorded | 69bcd4780636e5bf4afc2992 |
| TTC | 1.67 | Not recorded | 6923e676d6b0dd334292eee0 |
| TTC | 0.83 | Not recorded | 6923e676d6b0dd334292eee0 |
| CLIP | 0.12 | Not recorded | 69bcd4780636e5bf4afc2992 |

### ATAC

Average Robust Accuracy: 86.27. Result ID: 69d4d19047f34ce924bcfe0c.

[Reporting paper](<https://www.sota2.com/research/paper/6923e676d6b0dd334292eee0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6923e676d6b0dd334292eee0.md>)

Recorded evaluation configuration: {"Attack Strategy":"PGD","Epsilon":"4/255"}. This record does not assert independent reproduction.

### Comp-TGA

Average Robust Accuracy: 19.36. Result ID: 69bd12d047f34ce924a76f7a.

[Reporting paper](<https://www.sota2.com/research/paper/69bcd4780636e5bf4afc2992.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69bcd4780636e5bf4afc2992.md>)

Recorded evaluation configuration: {"Zero-shot":"true"}. This record does not assert independent reproduction.

### TGA-ZSR

Average Robust Accuracy: 14.43. Result ID: 69bd12d047f34ce924a76f79.

[Reporting paper](<https://www.sota2.com/research/paper/69bcd4780636e5bf4afc2992.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69bcd4780636e5bf4afc2992.md>)

Recorded evaluation configuration: {"Zero-shot":"true"}. This record does not assert independent reproduction.

### PMG-AFT

Average Robust Accuracy: 13.29. Result ID: 69bd12d047f34ce924a76f78.

[Reporting paper](<https://www.sota2.com/research/paper/69bcd4780636e5bf4afc2992.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72df1e209131cea5912e.md>)

Recorded evaluation configuration: {"Zero-shot":"true"}. This record does not assert independent reproduction.

### LAAT

Average Robust Accuracy: 12.87. Result ID: 69bd12d047f34ce924a76f77.

[Reporting paper](<https://www.sota2.com/research/paper/69bcd4780636e5bf4afc2992.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72701e209131cea5651c.md>)

Recorded evaluation configuration: {"Zero-shot":"true"}. This record does not assert independent reproduction.

### ATAC

Average Robust Accuracy: 11.25. Result ID: 69d4d19047f34ce924bcfe10.

[Reporting paper](<https://www.sota2.com/research/paper/6923e676d6b0dd334292eee0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6923e676d6b0dd334292eee0.md>)

Recorded evaluation configuration: {"Attack Strategy":"Avoid","Epsilon":"4/255","Running time (s)":"0.652"}. This record does not assert independent reproduction.

### FT-Adv.

Average Robust Accuracy: 11.06. Result ID: 69bd12d047f34ce924a76f74.

[Reporting paper](<https://www.sota2.com/research/paper/69bcd4780636e5bf4afc2992.md>)

Recorded evaluation configuration: {"Zero-shot":"true"}. This record does not assert independent reproduction.

### TTC

Average Robust Accuracy: 9.06. Result ID: 69d4d19047f34ce924bcfe0b.

[Reporting paper](<https://www.sota2.com/research/paper/6923e676d6b0dd334292eee0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa774a1e209131cea724cc.md>)

[Implementation](<https://www.sota2.com/here>)

Recorded evaluation configuration: {"Attack Strategy":"PGD","Epsilon":"4/255"}. This record does not assert independent reproduction.

### TeCoA

Average Robust Accuracy: 8.12. Result ID: 69bd12d047f34ce924a76f75.

[Reporting paper](<https://www.sota2.com/research/paper/69bcd4780636e5bf4afc2992.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f271e209131cea44177.md>)

Recorded evaluation configuration: {"Zero-shot":"true"}. This record does not assert independent reproduction.

### ATAC

Average Robust Accuracy: 5.83. Result ID: 69d4d19047f34ce924bcfe0e.

[Reporting paper](<https://www.sota2.com/research/paper/6923e676d6b0dd334292eee0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6923e676d6b0dd334292eee0.md>)

Recorded evaluation configuration: {"Attack Strategy":"Lure","Epsilon":"4/255","Running time (s)":"0.650"}. This record does not assert independent reproduction.

### FT-Clean

Average Robust Accuracy: 4.65. Result ID: 69bd12d047f34ce924a76f73.

[Reporting paper](<https://www.sota2.com/research/paper/69bcd4780636e5bf4afc2992.md>)

Recorded evaluation configuration: {"Zero-shot":"true"}. This record does not assert independent reproduction.

### FARE

Average Robust Accuracy: 4.23. Result ID: 69bd12d047f34ce924a76f76.

[Reporting paper](<https://www.sota2.com/research/paper/69bcd4780636e5bf4afc2992.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa738c1e209131cea5d24a.md>)

Recorded evaluation configuration: {"Zero-shot":"true"}. This record does not assert independent reproduction.

### TTC

Average Robust Accuracy: 1.67. Result ID: 69d4d19047f34ce924bcfe0f.

[Reporting paper](<https://www.sota2.com/research/paper/6923e676d6b0dd334292eee0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa774a1e209131cea724cc.md>)

[Implementation](<https://www.sota2.com/here>)

Recorded evaluation configuration: {"Attack Strategy":"Avoid","Epsilon":"4/255","Running time (s)":"0.114"}. This record does not assert independent reproduction.

### TTC

Average Robust Accuracy: 0.83. Result ID: 69d4d19047f34ce924bcfe0d.

[Reporting paper](<https://www.sota2.com/research/paper/6923e676d6b0dd334292eee0.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa774a1e209131cea724cc.md>)

[Implementation](<https://www.sota2.com/here>)

Recorded evaluation configuration: {"Attack Strategy":"Lure","Epsilon":"4/255","Running time (s)":"0.150"}. This record does not assert independent reproduction.

### CLIP

Average Robust Accuracy: 0.12. Result ID: 69bd12d047f34ce924a76f72.

[Reporting paper](<https://www.sota2.com/research/paper/69bcd4780636e5bf4afc2992.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69581e209131cea21ad0.md>)

[Implementation](<https://github.com/OpenAI/CLIP>)

Recorded evaluation configuration: {"Zero-shot":"true"}. This record does not assert independent reproduction.

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