Defense GAN

Reported on 2 benchmarks across 1 task · 1 paper · 2 SOTA

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

Adversarial2 results

Adversarial DefenseonMNIST
Accuracy· 2018-05-17
0.8529
SOTA
Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models arXiv:1805.06605
Adversarial DefenseonMNIST
Inference speed· 2018-05-17
14.8
best: 0.11 (PuVAE)
SOTA
Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models arXiv:1805.06605