# Adversarial Robustness Evaluation on CIFAR-100 (test) (Metrics: Clean, CC, FGSM, HRS)

Source: [Adversarial Robustness Evaluation on CIFAR-100 (test) (Metrics: Clean, CC, FGSM, HRS)](<https://www.sota2.com/research/sota/adversarial-robustness-evaluation-on-cifar-100-test-metrics-clean-cc-fgsm-hrs>)

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

Data updated: 2026-02-26T05:39:16.133Z

Evaluation of Image Classification model performance on the CIFAR-100 test set, specifically reporting clean accuracy alongside metrics related to adversarial attacks (FGSM) and custom robustness measures (CC, HRS).

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 (test) |
| Metric | Clean Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 7 of 7 |
| 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

- [Clean Accuracy](<https://www.sota2.com/research/sota/adversarial-robustness-evaluation-on-cifar-100-test-metrics-clean-cc-fgsm-hrs.md?metric=Clean%20Accuracy>): Higher is better; unit: PERCENT.

- [CC Score](<https://www.sota2.com/research/sota/adversarial-robustness-evaluation-on-cifar-100-test-metrics-clean-cc-fgsm-hrs.md?metric=CC%20Score>): Higher is better; unit: PERCENT.

- [FGSM Accuracy](<https://www.sota2.com/research/sota/adversarial-robustness-evaluation-on-cifar-100-test-metrics-clean-cc-fgsm-hrs.md?metric=FGSM%20Accuracy>): Higher is better; unit: PERCENT.

- [HRS Score](<https://www.sota2.com/research/sota/adversarial-robustness-evaluation-on-cifar-100-test-metrics-clean-cc-fgsm-hrs.md?metric=HRS%20Score>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Clean Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| PC-DARTS | 76.95 | Not recorded | 68fa70e81e209131cea4de59 |
| RobNet | 76.4 | Not recorded | 68fa70e81e209131cea4de59 |
| SynFlow | 76.23 | Not recorded | 68fa70e81e209131cea4de59 |
| DrNAS | 75.49 | Not recorded | 68fa70e81e209131cea4de59 |
| CRoZe | 75.46 | Not recorded | 68fa70e81e209131cea4de59 |
| AdvRush | 74.48 | Not recorded | 68fa70e81e209131cea4de59 |
| GradNorm | 68.52 | Not recorded | 68fa70e81e209131cea4de59 |

### PC-DARTS

Clean Accuracy: 76.95. Result ID: 699160a03a6c31484907bcf6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70e81e209131cea4de59.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67511e209131cea1563d.md>)

[Implementation](<https://github.com/yuhuixu1993/PC-DARTS>)

Recorded evaluation configuration: {"Training-free NAS":false,"Params (M)":3.6,"Search Time (GPU sec)":8355}. This record does not assert independent reproduction.

### RobNet

Clean Accuracy: 76.4. Result ID: 699160a03a6c31484907bcf8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70e81e209131cea4de59.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67411e209131cea154a0.md>)

Recorded evaluation configuration: {"Training-free NAS":false,"Params (M)":5.44,"Search Time (GPU sec)":274062}. This record does not assert independent reproduction.

### SynFlow

Clean Accuracy: 76.23. Result ID: 699160a03a6c31484907bcfb.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70e81e209131cea4de59.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69961e209131cea22e24.md>)

Recorded evaluation configuration: {"Training-free NAS":true,"Params (M)":4.42,"Search Time (GPU sec)":9776}. This record does not assert independent reproduction.

### DrNAS

Clean Accuracy: 75.49. Result ID: 699160a03a6c31484907bcf7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70e81e209131cea4de59.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69941e209131cea22d24.md>)

[Implementation](<https://github.com/xiangning-chen/DrNAS>)

Recorded evaluation configuration: {"Training-free NAS":false,"Params (M)":4.1,"Search Time (GPU sec)":46857}. This record does not assert independent reproduction.

### CRoZe

Clean Accuracy: 75.46. Result ID: 699160a03a6c31484907bcfc.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70e81e209131cea4de59.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70e81e209131cea4de59.md>)

[Implementation](<https://github.com/HyeonjeongHa/CRoZe>)

Recorded evaluation configuration: {"Training-free NAS":true,"Params (M)":4.72,"Search Time (GPU sec)":17457}. This record does not assert independent reproduction.

### AdvRush

Clean Accuracy: 74.48. Result ID: 699160a03a6c31484907bcf9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70e81e209131cea4de59.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6a931e209131cea2905e.md>)

Recorded evaluation configuration: {"Training-free NAS":false,"Params (M)":4.2,"Search Time (GPU sec)":251245}. This record does not assert independent reproduction.

### GradNorm

Clean Accuracy: 68.52. Result ID: 699160a03a6c31484907bcfa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa70e81e209131cea4de59.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa69961e209131cea22e24.md>)

Recorded evaluation configuration: {"Training-free NAS":true,"Params (M)":3.83,"Search Time (GPU sec)":9554}. This record does not assert independent reproduction.

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