Share your thoughts, 1 month free Claude Pro on usSee more

Certified Robustness on ImageNet

71.6Certified Accuracy (L1 R=0.5)

Uniform, LBS

Updated 27d ago

Evaluation Results

Method	Links
Uniform, LBS 2026.04		71.6	66.3	61.4	54.6	52.5	49.9	-	-	-
Laplace, LBS 2026.04		70.5	63.1	57	52.8	50.7	48.1	-	-	-
Uniform (w/), Yang et al. (2020) 2026.04		53.6	48.2	42.5	37.7	35.1	30.8	-	-	-
Laplace (w/), Teng et al. (2020) 2026.04		47.1	39.7	31.6	26.5	23	18.2	-	-	-
Laplace (w/), Lecuyer et al. (2019) 2026.04		42.8	39.5	34.2	22.8	18.9	10.4	-	-	-
Laplace (w/o), Teng et al. (2020) 2026.04		5.8	4.2	2.9	2.1	1.4	0.7	-	-	-
Uniform (w/o), Yang et al. (2020) 2026.04		5.7	2.7	2	1.6	1.1	0.7	-	-	-
Laplace (w/o), Lecuyer et al. (2019) 2026.04		5.4	3.9	3	2.2	1.8	1	-	-	-
Meta-1-Dynamic-Margin 2026.06		-	-	-	-	-	-	76.2	2.47	232.773
KT Prior 2026.06		-	-	-	-	-	-	76.2	5.18	232.77
Meta-1-Dynamic-Margin 2026.06		-	-	-	-	-	-	73.8	2.49	263.36
KT Prior 2026.06		-	-	-	-	-	-	73.8	4.9	263.36
Meta-1-Dynamic-Margin 2026.06		-	-	-	-	-	-	72.4	3.33	534.783
KT Prior 2026.06		-	-	-	-	-	-	72.4	5.28	288.41