PuVAE

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

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

Adversarial2 results

Adversarial DefenseonMNIST
Inference speed· 2019-03-02
0.11
SOTA
PuVAE: A Variational Autoencoder to Purify Adversarial Examples arXiv:1903.00585
Adversarial DefenseonMNIST
Accuracy· 2019-03-02
0.8133
best: 0.8529 (Defense GAN)
PuVAE: A Variational Autoencoder to Purify Adversarial Examples arXiv:1903.00585