search

val-iisc / GAMA-GAT

Guided Adversarial Attack for Evaluating and Enhancing Adversarial Defenses, NeurIPS Spotlight 2020
24 stars 9 forks source link

Some problems #5

Closed jiaxiaojunQAQ closed 1 year ago

jiaxiaojunQAQ commented 2 years ago
  1. The used ResNet is is different from the previous work, it has an extra layer ReLU?
  2. Whether the results reported in the paper are optimal or final checkpoints?
SravantiAddepalli commented 2 years ago

Hi @jiaxiaojunQAQ,

We used the ResNet-18 architecture from the following repository: https://github.com/yichuan9527/pytorch-cifar/blob/master/models/resnet.py Yes, there is an additional ReLU layer compared to the standard ResNet-18 model. However, we do not expect the results to be significantly different with the standard model as well.

The results reported in the paper are for optimal checkpoints. We select the best model based on I-FGSM 7-step accuracy on a hold-out validation set. The code for selection of best model is also present in the same file that is used for training models.