Skip to content

Releases: bethgelab/foolbox

Version 2.0.0 with batch support, model and defense zoo, threshold support and more

23 Oct 14:07
9d73dea
Compare
Choose a tag to compare

foolbox.attacks now refers to the attacks with batch support. The old attacks can still be accessed under foolbox.v1.attacks. Batch support has been added to almost all attacks and new attacks will only be implemented with batch support. If you need batch support for an old attack that has not yet been adapted, please open an issue.

Version 2.0.0rc0

18 Oct 10:40
09d2f68
Compare
Choose a tag to compare
Version 2.0.0rc0 Pre-release
Pre-release
Merge pull request #378 from jonasrauber/rc

2.0.0rc0

Version 2.0.0b0

21 May 19:21
Compare
Choose a tag to compare
Version 2.0.0b0 Pre-release
Pre-release

Batch-support is finally here!

See #316 for details until we have updated the documentation. Right now it's still limited to a few attacks, but feel free to open an issue for any attack that you need. It's easy to extend to new attacks, we just haven't done it yet and will prioritize based on requests.

Version 1.8.0

16 Nov 16:19
Compare
Choose a tag to compare

Foolbox Model Zoo

Foolbox now has an easy way to load models or defenses from Git repos: https://foolbox.readthedocs.io/en/latest/user/zoo.html

Version 1.7.0

24 Oct 07:41
Compare
Choose a tag to compare

New Features

Bug Fixes

  • Foolbox now uses its own random number generators to be independent of seeds set inside models.

Version 1.6.2

12 Oct 10:21
Compare
Choose a tag to compare

added missing backward() support to the CompositeModel model wrapper

Version 1.6.1

08 Oct 10:58
Compare
Choose a tag to compare

The foolbox.models.TensorFlowModel.from_keras constructor now automatically uses the session used by tf.keras instead of TensorFlow's default session.

Version 1.6.0

05 Oct 12:40
Compare
Choose a tag to compare

New features

Version 1.5.0

27 Sep 15:57
Compare
Choose a tag to compare

New features

  • all Foolbox attacks now support early stopping when reaching a certain perturbation size
    • just pass a threshold to the attack or Adversarial instance during initialization
  • the distance metric can now be passed to the attack during initialization (no need to manually create a Adversarial instance anymore)

Version 1.4.0

18 Sep 12:31
Compare
Choose a tag to compare
  • The Adversarial class now remembers the model output for the best adversarial so far. For deterministic models this is the same as fmodel.predictions(adversarial.image), but it can be useful for non-deterministic models. Note that very close to the decision boundary even otherwise deterministic models can become stochastic because of non-deterministic floating point operations such as reduce_sum. In addtion to the new output attribute, there is also a new adversarial_class attribute for convience; it just takes the argmax of the output.
  • new ADefAttack thanks to @EvgeniaAR
  • new NewtonFoolAttack thanks to @bveliqi
  • new FAQ section in the docs: https://foolbox.readthedocs.io/en/latest/user/faq.html