Pretrained models for evaluating adversarial robustness

Question

Pretrained models for evaluating adversarial robustness

Closed this issue 3 years ago · 1 comments

Gavin-1995 commented 3 years ago

Hi Hendrycks,

I want to evaluate the adversarial robustness of your proposed method about the datasets CIFAR10 and CIFAR100, can you provide the pretrained models of the proposed method about these two datasets?
Thank you!

Best wishes,
Gavin

Answer 1 · 2022-04-09T23:40:11.000Z

Hi,
https://github.com/hendrycks/pre-training/tree/master/robustness/adversarial
"Snapshots can be downloaded at https://drive.google.com/drive/folders/1bqipqqZF8hTcEP4Kn0lb8TfH4Sny6ANX?usp=sharing"