# Machine Unlearning on CIFAR-10 (retain)

Source: [Machine Unlearning on CIFAR-10 (retain)](<https://www.sota2.com/research/sota/machine-unlearning-on-cifar-10-retain>)

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

Data updated: 2026-02-26T05:30:28.830Z

Evaluation of Machine Unlearning effectiveness on the CIFAR-10 dataset, focusing specifically on the 'Accuracy' metric, likely representing performance on retained data.

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 | Machine Unlearning |
| Dataset (including any stated split) | CIFAR-10 (retain) |
| Metric | Accuracy |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 9 of 9 |
| 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

- [Accuracy](<https://www.sota2.com/research/sota/machine-unlearning-on-cifar-10-retain.md?metric=Accuracy>): Higher is better; unit: PERCENT.

## Recorded results

| Method | Accuracy | Result date | Report paper |
| --- | --- | --- | --- |
| Retrain | 100 | Not recorded | 68fa77cb1e209131cea75615 |
| Finetune | 100 | Not recorded | 68fa77cb1e209131cea75615 |
| SCRUB | 100 | Not recorded | 68fa77cb1e209131cea75615 |
| BadT | 100 | Not recorded | 68fa77cb1e209131cea75615 |
| ESC | 100 | Not recorded | 68fa77cb1e209131cea75615 |
| SalUn | 99.99 | Not recorded | 68fa77cb1e209131cea75615 |
| RL | 99.97 | Not recorded | 68fa77cb1e209131cea75615 |
| ESC-T | 97.78 | Not recorded | 68fa77cb1e209131cea75615 |
| NG | 96.59 | Not recorded | 68fa77cb1e209131cea75615 |

### Retrain

Accuracy: 100. Result ID: 69956b233badfaffe65f4fa4.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77cb1e209131cea75615.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa669c1e209131cea1168a.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","Number of trials":3,"Run Time Efficiency (s)":2681.72}. This record does not assert independent reproduction.

### Finetune

Accuracy: 100. Result ID: 69956b233badfaffe65f4fa5.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77cb1e209131cea75615.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70381e209131cea49a4c.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","Number of trials":3,"Run Time Efficiency (s)":132.02}. This record does not assert independent reproduction.

### SCRUB

Accuracy: 100. Result ID: 69956b233badfaffe65f4fa7.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77cb1e209131cea75615.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa71011e209131cea4e7b9.md>)

[Implementation](<https://github.com/Meghdad92/SCRUB>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","Number of trials":3,"Uses Retain set (Dr)":true,"Run Time Efficiency (s)":160.39}. This record does not assert independent reproduction.

### BadT

Accuracy: 100. Result ID: 69956b233badfaffe65f4fa8.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77cb1e209131cea75615.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f961e209131cea46745.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","Number of trials":3,"Run Time Efficiency (s)":182.78}. This record does not assert independent reproduction.

### ESC

Accuracy: 100. Result ID: 69956b233badfaffe65f4fab.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77cb1e209131cea75615.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77cb1e209131cea75615.md>)

[Implementation](<https://github.com/KU-VGI/ESC>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","Number of trials":3,"Uses Retain set (Dr)":false,"Run Time Efficiency (s)":2.24}. This record does not assert independent reproduction.

### SalUn

Accuracy: 99.99. Result ID: 69956b233badfaffe65f4fa9.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77cb1e209131cea75615.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72cd1e209131cea5888f.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","Number of trials":3,"Run Time Efficiency (s)":150.51}. This record does not assert independent reproduction.

### RL

Accuracy: 99.97. Result ID: 69956b233badfaffe65f4fa6.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77cb1e209131cea75615.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67551e209131cea158d5.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","Number of trials":3,"Run Time Efficiency (s)":2.57}. This record does not assert independent reproduction.

### ESC-T

Accuracy: 97.78. Result ID: 69956b233badfaffe65f4fac.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77cb1e209131cea75615.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa77cb1e209131cea75615.md>)

[Implementation](<https://github.com/KU-VGI/ESC>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","Number of trials":3,"Uses Retain set (Dr)":false,"Run Time Efficiency (s)":29.47}. This record does not assert independent reproduction.

### NG

Accuracy: 96.59. Result ID: 69956b233badfaffe65f4faa.

[Reporting paper](<https://www.sota2.com/research/paper/68fa77cb1e209131cea75615.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6bf01e209131cea31038.md>)

Recorded evaluation configuration: {"Backbone":"ResNet-18","Number of trials":3,"Run Time Efficiency (s)":26.79}. This record does not assert independent reproduction.

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