# Robustness Verification on tinyimagenet 2024

Source: [Robustness Verification on tinyimagenet 2024](<https://www.sota2.com/research/sota/robustness-verification-on-tinyimagenet-2024>)

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

Data updated: 2026-02-26T06:08:14.991Z

Evaluation of model robustness verification performance on the tinyimagenet 2024 dataset, measuring verified accuracy and the time required for verification.

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 | Robustness Verification |
| Dataset (including any stated split) | tinyimagenet 2024 |
| Metric | Verified Accuracy (%) |
| Unit | PERCENT |
| Direction | Higher 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

- [Verified Accuracy (%)](<https://www.sota2.com/research/sota/robustness-verification-on-tinyimagenet-2024.md?metric=Verified%20Accuracy%20(%25)>): Higher is better; unit: PERCENT.

- [Avg Verification Time (s)](<https://www.sota2.com/research/sota/robustness-verification-on-tinyimagenet-2024.md?metric=Avg%20Verification%20Time%20(s)>): Lower is better; unit: TIME.

## Recorded results

| Method | Verified Accuracy (%) | Result date | Report paper |
| --- | --- | --- | --- |
| Clip-and-Verify | 72 | Not recorded | 693f96136cfd488761a81bef |
| Clip-and-Verify | 70 | Not recorded | 693f96136cfd488761a81bef |
| BICCOS | 69 | Not recorded | 693f96136cfd488761a81bef |
| β-CROWN | 67.5 | Not recorded | 693f96136cfd488761a81bef |

### Clip-and-Verify

Verified Accuracy (%): 72. Result ID: 69996cda5698665ec4da9b1b.

[Reporting paper](<https://www.sota2.com/research/paper/693f96136cfd488761a81bef.md>)

[Method origin paper](<https://www.sota2.com/research/paper/693f96136cfd488761a81bef.md>)

Recorded evaluation configuration: {"Model":"tinyimagenet-2024","Verifier Backend":"BICCOS"}. This record does not assert independent reproduction.

### Clip-and-Verify

Verified Accuracy (%): 70. Result ID: 69996cda5698665ec4da9b1a.

[Reporting paper](<https://www.sota2.com/research/paper/693f96136cfd488761a81bef.md>)

[Method origin paper](<https://www.sota2.com/research/paper/693f96136cfd488761a81bef.md>)

Recorded evaluation configuration: {"Model":"tinyimagenet-2024","Verifier Backend":"β-CROWN"}. This record does not assert independent reproduction.

### BICCOS

Verified Accuracy (%): 69. Result ID: 69996cda5698665ec4da9b19.

[Reporting paper](<https://www.sota2.com/research/paper/693f96136cfd488761a81bef.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5cc91e209131ce9d452a.md>)

[Implementation](<https://github.com/Lemutisme/BICCOS>)

Recorded evaluation configuration: {"Model":"tinyimagenet-2024"}. This record does not assert independent reproduction.

### β-CROWN

Verified Accuracy (%): 67.5. Result ID: 69996cda5698665ec4da9b18.

[Reporting paper](<https://www.sota2.com/research/paper/693f96136cfd488761a81bef.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa65031e209131cea07e5a.md>)

Recorded evaluation configuration: {"Model":"tinyimagenet-2024"}. This record does not assert independent reproduction.

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