Ours (Stochastic-LWTA/PGD/WideResNet-34-1)

Reported on 2 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Adversarial2 results

Adversarial DefenseonCIFAR-10
Accuracy· 2021-12-05
81.87
best: 90.03 (WRN-28-10)
Stochastic Local Winner-Takes-All Networks Enable Profound Adversarial Robustness arXiv:2112.02671
Adversarial DefenseonCIFAR-10
Attack: AutoAttack· 2021-12-05
74.71
best: 82.6 (Stochastic-LWTA/PGD/WideResNet-34-10)
Stochastic Local Winner-Takes-All Networks Enable Profound Adversarial Robustness arXiv:2112.02671