A DIP-based optimization produces adversarial perturbations and patches that are more robust to affine transformations than standard high-frequency noise while staying imperceptible.
Foolbox: A Python toolbox to benchmark the robustness of machine learning models
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
abstract
Even todays most advanced machine learning models are easily fooled by almost imperceptible perturbations of their inputs. Foolbox is a new Python package to generate such adversarial perturbations and to quantify and compare the robustness of machine learning models. It is build around the idea that the most comparable robustness measure is the minimum perturbation needed to craft an adversarial example. To this end, Foolbox provides reference implementations of most published adversarial attack methods alongside some new ones, all of which perform internal hyperparameter tuning to find the minimum adversarial perturbation. Additionally, Foolbox interfaces with most popular deep learning frameworks such as PyTorch, Keras, TensorFlow, Theano and MXNet and allows different adversarial criteria such as targeted misclassification and top-k misclassification as well as different distance measures. The code is licensed under the MIT license and is openly available at https://github.com/bethgelab/foolbox . The most up-to-date documentation can be found at http://foolbox.readthedocs.io .
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
ADIS-GAN disentangles affine transformations in a GAN to achieve over 98% classification accuracy on MNIST within 30 degrees rotation and over 90% under FGSM and PGD attacks while generating rotation and scaling factors.
citing papers explorer
-
Robust Synthesis of Adversarial Visual Examples Using a Deep Image Prior
A DIP-based optimization produces adversarial perturbations and patches that are more robust to affine transformations than standard high-frequency noise while staying imperceptible.
-
Affine Disentangled GAN for Interpretable and Robust AV Perception
ADIS-GAN disentangles affine transformations in a GAN to achieve over 98% classification accuracy on MNIST within 30 degrees rotation and over 90% under FGSM and PGD attacks while generating rotation and scaling factors.
- Evaluation of AI Ethics Tools in Language Models: A Developers' Perspective Case Study