A powerful white-box adversarial attack that exploits knowledge about the geometry of neural networks to find minimal adversarial perturbations without doing gradient descent
No README available, please check again later.
New distributional and shape attacks on neural networks that process 3D point cloud data.
Research on adversarial attacks and defenses for deep neural network 3D point cloud classifiers l...
NIPS 2017 Adversarial Competition in PyTorch
A PyTorch baseline attack example for the NIPS 2017 adversarial competition
A small course on exploiting and defending neural networks
Hands-on tutorial on adversarial examples 😈. With Streamlit app ❤️.
Source for paper "Attacking Binarized Neural Networks"
Robust evasion attacks against neural network to find adversarial examples
Code for our ICLR Trustworthy ML 2020 workshop paper "Improved Image Wasserstein Attacks and Defe...
A Python toolbox to create adversarial examples that fool neural networks in PyTorch, TensorFlow,...
Paper Collection of Adversarial Machine Learning
A PyTorch baseline defense example for the NIPS 2017 adversarial competition
Targeted Adversarial Examples for Black Box Audio Systems
Contains materials for workshops pertaining to adversarial robustness in deep learning.
Attax: adversarial attacks using JAX