Skip to main content
Help us improve Python packaging – donate today!

Python toolbox to create adversarial examples that fool neural networks

Project Description

https://readthedocs.org/projects/foolbox/badge/?version=latest https://travis-ci.org/bethgelab/foolbox.svg?branch=master

Foolbox

Foolbox is a Python toolbox to create adversarial examples that fool neural networks. It requires Python, NumPy and SciPy.

Installation

pip install foolbox

We test using Python 2.7, 3.5 and 3.6. Other Python versions might work as well. We recommend using Python 3!

Documentation

Documentation is available on readthedocs: http://foolbox.readthedocs.io/

Example

import foolbox
import keras
from keras.applications.resnet50 import ResNet50, preprocess_input

# instantiate model
keras.backend.set_learning_phase(0)
kmodel = ResNet50(weights='imagenet')
fmodel = foolbox.models.KerasModel(kmodel, bounds=(0, 255), preprocess_fn=preprocess_input)

# get source image and label
image, label = foolbox.utils.imagenet_example()

# apply attack on source image
attack  = foolbox.attacks.FGSM(fmodel)
adv_img = attack(image=image, label=label)

Interfaces for a range of other deeplearning packages such as TensorFlow, PyTorch and Lasagne are available, e.g.

model = foolbox.models.TensorFlowModel(images, logits, bounds=(0, 255))
model = foolbox.models.PyTorchModel(torchmodel, bounds=(0, 255), num_classes=1000)
# etc.

Different adversarial criteria such as Top-k, specific target classes or target probability levels can be passed to the attack, e.g.

criterion = foolbox.criteria.TargetClass(22)
attack    = foolbox.attacks.FGSM(fmodel, criterion)

Feature requests and bug reports

We welcome feature requests and bug reports. Just create a new issue on GitHub.

Questions

Depending on the nature of your question feel free to post it as an issue on GitHub, or post it as a question on Stack Overflow using the foolbox tag. We will try to monitor that tag but if you don’t get an answer don’t hesitate to contact us.

Development

Foolbox is a work in progress and any input is welcome.

Citation

If you find Foolbox useful for your scientific work, please consider citing it in resulting publications. We will soon publish a technical paper and will provide the citation here.

Release history Release notifications

History Node

1.1.0

History Node

1.0.0

History Node

0.15.0

History Node

0.14.0

History Node

0.13.0

History Node

0.12.4

History Node

0.12.3

History Node

0.12.2

History Node

0.12.1

History Node

0.11.1

History Node

0.11.0

History Node

0.10.0

History Node

0.9.6

History Node

0.9.5

History Node

0.9.4

History Node

0.9.3

History Node

0.9.2

History Node

0.9.1

History Node

0.9.0

History Node

0.8.1

History Node

0.8.0

History Node

0.7.3

History Node

0.7.2

History Node

0.7.1

History Node

0.7.0

History Node

0.6.0

This version
History Node

0.5.0

History Node

0.4.1

History Node

0.3.5

History Node

0.3.4

History Node

0.3.3

History Node

0.3.2

History Node

0.3.1

History Node

0.3

History Node

0.2

History Node

0.1b1

History Node

0.1a2

History Node

0.1a1

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Filename, size & hash SHA256 hash help File type Python version Upload date
foolbox-0.5.0.tar.gz (200.9 kB) Copy SHA256 hash SHA256 Source None Jun 19, 2017

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging CloudAMQP CloudAMQP RabbitMQ AWS AWS Cloud computing Fastly Fastly CDN DigiCert DigiCert EV certificate StatusPage StatusPage Status page