Closed jrounds closed 4 years ago
Hi. Sorry for the late response. The level of perturbation is expected given that our adversarial radius here is l_inf=0.1. If you want an image that looks less perturbed, you can adjust the l_inf=0.03. Specifically, you can adjust thee lr
parameter in PGD or CW in attack.py
by setting that to be 0.03. Thanks!
Hi,
Thanks for releasing your code. Replicating your work on new images to learn from you.
I did:
mkdir -P data/
python attack.py --setting=white --real_dir=data/real --adv_dir=data/adv_dir --name="run1" --base=inception > log_attack_white_inception_001.txt 2>&1
No problem everything ran fine.
Then I extracted the attack images from the tensors with:
Result Then i looked at the images. This is where I should say I have prior experience with CW attacks and in particular the cleverhans reference implementation. Generally speaking a correctly parameterized CW and DeepFool will not usually be noticeable to the human eye.
But these images from 4 are much different as they have splotching for cw attacked images:
Do you have a suggested parameterization of 3 that might result in a subtler CW?