# Robustness Evaluation (Attacks) on ImageNet (val)

Source: [Robustness Evaluation (Attacks) on ImageNet (val)](<https://www.sota2.com/research/sota/robustness-evaluation-attacks-on-imagenet-val>)

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

Data updated: 2026-02-26T05:39:19.296Z

Evaluation of Image Classification robustness on the validation split of the ImageNet dataset, specifically measuring performance under various semantic and full adversarial attacks, alongside clean accuracy.

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) | ImageNet (val) |
| Metric | Clean Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 0 of 0 |
| 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/robustness-evaluation-attacks-on-imagenet-val.md?metric=Clean%20Accuracy>): Higher is better; unit: PERCENT.

- [CAA3a Accuracy](<https://www.sota2.com/research/sota/robustness-evaluation-attacks-on-imagenet-val.md?metric=CAA3a%20Accuracy>): Higher is better; unit: PERCENT.

- [CAA3b Accuracy](<https://www.sota2.com/research/sota/robustness-evaluation-attacks-on-imagenet-val.md?metric=CAA3b%20Accuracy>): Higher is better; unit: PERCENT.

- [CAA3c Accuracy](<https://www.sota2.com/research/sota/robustness-evaluation-attacks-on-imagenet-val.md?metric=CAA3c%20Accuracy>): Higher is better; unit: PERCENT.

- [Semantic Acc (Rand.)](<https://www.sota2.com/research/sota/robustness-evaluation-attacks-on-imagenet-val.md?metric=Semantic%20Acc%20(Rand.)>): Higher is better; unit: PERCENT.

- [Semantic Acc (Sched.)](<https://www.sota2.com/research/sota/robustness-evaluation-attacks-on-imagenet-val.md?metric=Semantic%20Acc%20(Sched.)>): Higher is better; unit: PERCENT.

- [Full Acc (Rand.)](<https://www.sota2.com/research/sota/robustness-evaluation-attacks-on-imagenet-val.md?metric=Full%20Acc%20(Rand.)>): Higher is better; unit: PERCENT.

- [Full Acc (Sched.)](<https://www.sota2.com/research/sota/robustness-evaluation-attacks-on-imagenet-val.md?metric=Full%20Acc%20(Sched.)>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Clean Accuracy | Result date | Report paper |
| --- | --- | --- | --- |

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