Foolbox

New Features

* Foolbox now has support for the Spatial Attack (https://arxiv.org/abs/1712.02779)

Bug Fixes

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

added missing `backward()` support to the `CompositeModel` model wrapper

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

New features

* support for **TensorFlow Eager**: [TensorFlowEagerModel](https://foolbox.readthedocs.io/en/latest/modules/models.html#foolbox.models.TensorFlowEagerModel)
* improved support for **`tensorflow.keras`** models: [TensorFlowModel.from_keras(...)](https://foolbox.readthedocs.io/en/latest/modules/models.html#foolbox.models.TensorFlowModel.from_keras)
* Foolbox-native implementation of the **Carlini Wagner L2 attack**: [CarliniWagnerL2Attack](https://foolbox.readthedocs.io/en/latest/modules/attacks/gradient.html#foolbox.attacks.CarliniWagnerL2Attack)

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)

* 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](https://foolbox.readthedocs.io/en/latest/modules/attacks/gradient.html#foolbox.attacks.ADefAttack) thanks to EvgeniaAR
* new [NewtonFoolAttack](https://foolbox.readthedocs.io/en/latest/modules/attacks/gradient.html#foolbox.attacks.NewtonFoolAttack) thanks to bveliqi
* new FAQ section in the docs: https://foolbox.readthedocs.io/en/latest/user/faq.html