Skip to main content

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 https://coveralls.io/repos/github/bethgelab/foolbox/badge.svg

Foolbox

Foolbox is a Python toolbox to create adversarial examples that fool neural networks. It requires Python 3, NumPy and SciPy.

Installation

pip install foolbox

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.PyTorchModel(torchmodel)

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)

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.

Authors

Project details


Download files

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

Source Distribution

foolbox-0.4.1.tar.gz (199.8 kB view hashes)

Uploaded Source

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page