Support for foolbox attacks via a simple interface #166
Conversation
Codecov Report✅ All modified and coverable lines are covered by tests. 📢 Thoughts on this report? Let us know! |
There was a problem hiding this comment.
potentially leave out of mandatory dependencies
…RONA into henba1-foolbox-interface
| if data.dim() == 3: | ||
| data = data.unsqueeze(0) | ||
|
|
||
| if target.dim() == 0: |
There was a problem hiding this comment.
What happends when its a targeted attack?
There was a problem hiding this comment.
targeted attacks are currently not supported - the target here is the correct label
AttackEstimationModule.verify() currently always passes the true label (verification_context.data_point.label) as the "target"
| BinarySearchEpsilonValueEstimator, | ||
| ) | ||
| from ada_verona.verification_module.attack_estimation_module import AttackEstimationModule | ||
| from ada_verona.verification_module.attacks.foolbox_attack import FoolboxAttack |
There was a problem hiding this comment.
add the check whether foolbox is installed like we have for the other scripts
| from ada_verona.database.dataset.image_file_dataset import ImageFileDataset | ||
| from ada_verona.database.experiment_repository import ExperimentRepository | ||
| from ada_verona.dataset_sampler.predictions_based_sampler import PredictionsBasedSampler | ||
| from ada_verona.epsilon_value_estimator.binary_search_epsilon_value_estimator import ( |
There was a problem hiding this comment.
why do we need two example scripts for such a small different?
There was a problem hiding this comment.
its not mandatory though, treat like AutoAttack and AutoVerify\
add check for foolbox like we have for auto-verify and autoattack
|
I will check the tests later |
No description provided.