IBM/Autozoom-Attack

Bug report, the attacked classification model does not load any pre-trained weights!

Opened this issue · 1 comments

I can't find any saver.restore(sess, weight_path) code in main.py or blackbox_attack.py for loading classifier weights. Actually, this code attack the untrained classification model, which outputs almost random probabilities prediction?

We provided the pretrained model in this repo.

Please make sure you utilize this repo correctly and provide example code to support your issue.