Evasive trojan challenge uses incorrect `trojan_type` of `evasive_trojan` instead of `trojan_evasion`
carlini opened this issue · 2 comments
In train_batch_of_models.py
we see the following line:
but then further on down we see the other condition on the argument args.trojan_type
tdc-starter-kit/evasive_trojans/train_batch_of_models.py
Lines 65 to 75 in bf4384e
Therefore, args.trojan_type
can never be evasive_trojan
(or else we will ValueError
here) and so training_kwargs['num_epochs']
will always be 10
. Hopefully this will not cause you any issues in your pretrained models.
Hello,
Thank you for pointing this out! In early experiments, we found that using 20 epochs worked better for evasive Trojans on MNIST, but there have been several major changes to the baseline code since then, so we will just standardize it to always use 10 epochs (so this was a serendipitous bug :) ).
This did not affect the pretrained models in the evaluation server or the training data, so you should be able to make submissions now.
All the best,
Mantas
Thank you!