# Machine Unlearning on CIFAR-100 class lamp (test) Source: [Machine Unlearning on CIFAR-100 class lamp (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:34:58.962Z Evaluation of Machine Unlearning effectiveness on the specific 'class lamp' subset of the CIFAR-100 test set, reporting utility metrics (Ar, Af) and privacy leakage (MIA). 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 lamp (test) | | Metric | Ar (Accuracy Retention) | | 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 - [Ar (Accuracy Retention)](): Higher is better; unit: PERCENT. - [Af (Fidelity Accuracy)](): Higher is better; unit: PERCENT. - [MIA (Membership Inference Attack Success Rate)](): Lower is better; unit: PERCENT. ## Recorded results | Method | Ar (Accuracy Retention) | Result date | Report paper | | --- | --- | --- | --- | | baseline | 76.5 | Not recorded | 6997ea6609c33900fcd76493 | | SSD | 76.46 | Not recorded | 6997ea6609c33900fcd76493 | | MeGU | 76.11 | Not recorded | 6997ea6609c33900fcd76493 | | retrain | 75.33 | Not recorded | 6997ea6609c33900fcd76493 | | AMNC | 73.32 | Not recorded | 6997ea6609c33900fcd76493 | | UNSIR | 71.64 | Not recorded | 6997ea6609c33900fcd76493 | | FT | 64.74 | Not recorded | 6997ea6609c33900fcd76493 | ### baseline Ar (Accuracy Retention): 76.5. Result ID: 699b058f5698665ec497e4c4. [Reporting paper]() Recorded evaluation configuration: {"model":"RN18"}. This record does not assert independent reproduction. ### SSD Ar (Accuracy Retention): 76.46. Result ID: 699b05905698665ec497e4c9. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"model":"RN18"}. This record does not assert independent reproduction. ### MeGU Ar (Accuracy Retention): 76.11. Result ID: 699b05905698665ec497e4ca. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"model":"RN18"}. This record does not assert independent reproduction. ### retrain Ar (Accuracy Retention): 75.33. Result ID: 699b058f5698665ec497e4c5. [Reporting paper]() Recorded evaluation configuration: {"model":"RN18"}. This record does not assert independent reproduction. ### AMNC Ar (Accuracy Retention): 73.32. Result ID: 699b058f5698665ec497e4c8. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"model":"RN18"}. This record does not assert independent reproduction. ### UNSIR Ar (Accuracy Retention): 71.64. Result ID: 699b058f5698665ec497e4c7. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"model":"RN18"}. This record does not assert independent reproduction. ### FT Ar (Accuracy Retention): 64.74. Result ID: 699b058f5698665ec497e4c6. [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.