Image Classification and Reconstruction Defense on CIFAR100 (val test) benchmark leaderboard · SOTA2 Research

Image Classification and Reconstruction Defense on CIFAR100 (val test)

68.43AccuracyBottleneck

Evaluation Results

Method	Links
Bottleneck2025.03		68.43	0.0007	0.0007	0.0009	0.0008
Bottleneck+CEM2025.03		68.42	0.0058	0.0059	0.0019	0.002
ResSFL+CEM2025.03		66.96	0.0093	0.0095	0.0043	0.0046
ResSFL2025.03		66.94	0.0051	0.0052	0.0019	0.002
DistCorr+CEM2025.03		66.27	0.0074	0.0075	0.0044	0.0045
DistCorr2025.03		66.21	0.0054	0.0055	0.0023	0.0025
Dropout+CEM2025.03		65.92	0.006	0.0061	0.0031	0.0032
Dropout2025.03		65.85	0.0042	0.0043	0.0016	0.0018
Average w/o CEM2025.03		65.81	0.0117	0.012	0.0063	0.0073
Average w/ CEM2025.03		65.75	0.0165	0.0168	0.0095	0.0102
Noise_Nopeek2025.03		65.55	0.0063	0.0063	0.0037	0.0038
Noise_Nopeek+CEM2025.03		65.33	0.0083	0.0082	0.0052	0.0052
PATROL2025.03		65.1	0.0335	0.0346	0.0196	0.0238
PATROL+CEM2025.03		65.07	0.0419	0.0423	0.0235	0.0253
Noise_ARL2025.03		62.58	0.027	0.0277	0.0143	0.0164
Noise_ARL+CEM2025.03		62.34	0.0373	0.038	0.0219	0.0236