93 Open source projects that are alternatives of or similar to Foolbox

TrojanZoo provides a universal pytorch platform to conduct security researches (especially backdoor attacks/defenses) of image classification in deep learning.

CHOP: An optimization library based on PyTorch, with applications to adversarial examples and structured neural network training.

Natural Language Attacks in a Hard Label Black Box Setting.

[ICML 2019, 20 min long talk] Robust Decision Trees Against Adversarial Examples

A didactic Gaussian process package for researchers in Jax.

KitanaQA: Adversarial training and data augmentation for neural question-answering models

Repository of Jupyter notebook tutorials for teaching the Deep Learning Course at the University of Amsterdam (MSc AI), Fall 2022/Spring 2022

Attacking Optical Flow (ICCV 2019)

Provably defending pretrained classifiers including the Azure, Google, AWS, and Clarifai APIs

Randomized Smoothing of All Shapes and Sizes (ICML 2020).

JAX-based Spiking Neural Network framework

A GPT, made only of MLPs, in Jax

AdvPC: Transferable Adversarial Perturbations on 3D Point Clouds (ECCV 2020)

An Algorithm to Quantify Robustness of Recurrent Neural Networks

Geometric Adversarial Attacks and Defenses on 3D Point Clouds (3DV 2021)

Implementation of the WSDM 2021 paper "Node Similarity Preserving Graph Convolutional Networks"

Revisiting Rainbow

Unofficial JAX implementations of deep learning research papers

Computational Fluid Dynamics in JAX

Implementation of the KDD 2020 paper "Graph Structure Learning for Robust Graph Neural Networks"

JAX implementations of core Deep RL algorithms

No description or website provided.

Companion code in JAX for the paper Parallel Iterated Extended and Sigma-Point Kalman Smoothers.

ADAM implements a collection of algorithms for calculating rigid-body dynamics in Jax, CasADi, PyTorch, and Numpy.

Graph Robustness Benchmark: A scalable, unified, modular, and reproducible benchmark for evaluating the adversarial robustness of Graph Machine Learning.

JAX code for the paper "Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiation"

Pre-Training Buys Better Robustness and Uncertainty Estimates (ICML 2019)

Implemention of Fast Gradient Sign Method for generating adversarial examples in Keras

Graphsignal Python agent

Deep learning operations reinvented (for pytorch, tensorflow, jax and others)

🔮 A refreshing functional take on deep learning, compatible with your favorite libraries

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

TFDS is a collection of datasets ready to use with TensorFlow, Jax, ...