bug in saving targets

poisoning-benchmark/poison_crafting/craft_poisons_bp.py

Line 178 in 9445c3e

target = un_normalize_data(target.squeeze(0))

I believe you need to also pass 'args.dataset' to un_normalize_data, or else the target may be unnormalized from a different base distribution (the default CIFAR10 one) than what the poisons and all the rest of the data belongs to

Thank you for pointing this out. We are going to look into it and follow up shortly.

Great, thanks. I came across this by noticing that the misclassification error in a transfer learning (fixed feature encoder) was very high, even without poisons in the fine tuning set. Upon further inspection, I was surprised to see that the saved target image differed quite a bit from the image in the test set that it was supposed to match (according to the target index in the poison setup dict). If you come across anything that may explain this, I'd greatly appreciate it if you let me know. Nice paper btw!!

nvm on that last note. congrats again on the great work!

Hi, I have committed a change to fix this bug. Thank you for bringing it to our attention. I re-ran the benchmark tests and saw no change. Does this resolve the issue?