Image Classification on CIFAR-100 (Adversarial Robustness via FGSM/PGD) benchmark leaderboard · SOTA2 Research

Image Classification on CIFAR-100 (Adversarial Robustness via FGSM/PGD)

73.85Clean AccuracyDLIF

Evaluation Results

Method	Links
DLIF2026.02		73.85	8.08	—	0	0	0	0
Vanilla2026.02		73.46	6.36	11.15	0.01	0	0	0
Vanilla2026.02		71.42	5.92	24.95	0.18	0.07	0.04	0.02
DLIF2026.02		70.79	6.95	—	0.08	0.05	0	0
StoG2026.02		70.44	8.27	—	0.49	—	—	—
TGO2026.02		69.47	17.2	38.23	2.3	1.33	0.69	0.42
SR2026.02		69.15	9.84	34.43	1.22	0.86	0.52	0.3
TGO2026.02		69.04	23.9	41.17	3.26	1.84	0.67	0.35
AT2026.02		68.57	21.18	46.6	11.14	9.22	7.5	6.72
RAT2026.02		67.76	20.87	46.21	11.14	9.34	7.66	6.9
RAT2026.02		67.59	25.07	48.92	13.6	11.41	9.07	8.35
DLIF2026.02		66.57	33.05	—	18.75	16.23	12.16	9.44
StoG2026.02		66.37	23.45	—	14.42	—	—	—
AT2026.02		66.27	17.2	45.13	8.3	9.62	8.16	7.52
TGO2026.02		65.93	24.16	47.9	12.83	10.12	8.72	6.59
DLIF2026.02		65.86	25.9	—	15.2	14.03	13.37	13.3
TGO2026.02		65.64	33.84	51.44	18.84	14.59	10.57	8.9
TGO2026.02		64.49	41.99	55.01	27.78	22.75	15.99	12.91
TGO2026.02		64.22	40.35	54.53	25.79	20.93	14.02	10.77
SR2026.02		62.8	28.27	48.91	21.93	18.46	12.28	9.78
StoG2026.02		62.26	33.4	—	23.15	—	—	—