Machine Unlearning Effectiveness Assessment on CIFAR-10 (UA/MIA Focus) benchmark leaderboard · SOTA2 Research

Machine Unlearning Effectiveness Assessment on CIFAR-10 (UA/MIA Focus)

100Unlearning Accuracy (UA)RT

Evaluation Results

Method	Links
RT2025.05		100	100	99.98	90.37	100	0	104.93
RL2025.05		100	100	96.67	87.81	100	1.17	6.8
SFRon2025.05		100	100	83.46	81.8	100	5.02	18.59
SalUn2025.05		100	100	99.81	90.34	100	0.04	6.97
MCUβ2025.05		100	100	99.85	90.37	100	0.03	7.29
MCU2025.05		99.96	100	99.8	90.37	100	0.04	7.27
NegGrad+2025.05		99.94	100	98.07	87.25	99.97	1.02	2.95
GA2025.05		85.01	88.5	90.55	80.9	86.27	11.82	0.4
NegTV2025.05		25.28	31.95	93.03	82.43	29.05	45.72	0.71
FT2025.05		18.53	24.63	99.94	91.01	43.18	42.87	5.52