# Machine Unlearning on CIFAR-100 class wolf (test) Source: [Machine Unlearning on CIFAR-100 class wolf (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:34:37.264Z Evaluation of Machine Unlearning effectiveness specifically on the subset of the CIFAR-100 test set corresponding only to the 'wolf' class, reporting utility (Ar, Af) and privacy (MIA) metrics. 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-100 class wolf (test) | | Metric | Accuracy Retention (Ar) | | 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 - [Accuracy Retention (Ar)](): Higher is better; unit: PERCENT. - [Accuracy Forgetting (Af)](): Higher is better; unit: PERCENT. - [MIA Success Rate](): Higher is better; unit: PERCENT. ## Recorded results | Method | Accuracy Retention (Ar) | Result date | Report paper | | --- | --- | --- | --- | | baseline | 76.38 | Not recorded | 6997ea6609c33900fcd76493 | | MeGU | 76.3 | Not recorded | 6997ea6609c33900fcd76493 | | retrain | 76.28 | Not recorded | 6997ea6609c33900fcd76493 | | SSD | 76.26 | Not recorded | 6997ea6609c33900fcd76493 | | AMNC | 72.64 | Not recorded | 6997ea6609c33900fcd76493 | | UNSIR | 71.75 | Not recorded | 6997ea6609c33900fcd76493 | | FT | 63.45 | Not recorded | 6997ea6609c33900fcd76493 | ### baseline Accuracy Retention (Ar): 76.38. Result ID: 699b05905698665ec497e4d9. [Reporting paper]() Recorded evaluation configuration: {"model":"RN18"}. This record does not assert independent reproduction. ### MeGU Accuracy Retention (Ar): 76.3. Result ID: 699b05905698665ec497e4df. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"model":"RN18"}. This record does not assert independent reproduction. ### retrain Accuracy Retention (Ar): 76.28. Result ID: 699b05905698665ec497e4da. [Reporting paper]() Recorded evaluation configuration: {"model":"RN18"}. This record does not assert independent reproduction. ### SSD Accuracy Retention (Ar): 76.26. Result ID: 699b05905698665ec497e4de. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"model":"RN18"}. This record does not assert independent reproduction. ### AMNC Accuracy Retention (Ar): 72.64. Result ID: 699b05905698665ec497e4dd. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"model":"RN18"}. This record does not assert independent reproduction. ### UNSIR Accuracy Retention (Ar): 71.75. Result ID: 699b05905698665ec497e4dc. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"model":"RN18"}. This record does not assert independent reproduction. ### FT Accuracy Retention (Ar): 63.45. Result ID: 699b05905698665ec497e4db. [Reporting paper]() Recorded evaluation configuration: {"model":"RN18"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.