trojanzooTrojanZoo provides a universal pytorch platform to conduct security researches (especially backdoor attacks/defenses) of image classification in deep learning.
Stars: ✭ 178 (-91.56%)
chopCHOP: An optimization library based on PyTorch, with applications to adversarial examples and structured neural network training.
Stars: ✭ 68 (-96.77%)
hard-label-attackNatural Language Attacks in a Hard Label Black Box Setting.
Stars: ✭ 26 (-98.77%)
RobustTrees[ICML 2019, 20 min long talk] Robust Decision Trees Against Adversarial Examples
Stars: ✭ 62 (-97.06%)
GPJaxA didactic Gaussian process package for researchers in Jax.
Stars: ✭ 159 (-92.46%)
KitanaQAKitanaQA: Adversarial training and data augmentation for neural question-answering models
Stars: ✭ 58 (-97.25%)
uvadlc notebooksRepository of Jupyter notebook tutorials for teaching the Deep Learning Course at the University of Amsterdam (MSc AI), Fall 2022/Spring 2022
Stars: ✭ 901 (-57.26%)
flowattackAttacking Optical Flow (ICCV 2019)
Stars: ✭ 58 (-97.25%)
denoised-smoothingProvably defending pretrained classifiers including the Azure, Google, AWS, and Clarifai APIs
Stars: ✭ 82 (-96.11%)
rs4aRandomized Smoothing of All Shapes and Sizes (ICML 2020).
Stars: ✭ 47 (-97.77%)
rA9JAX-based Spiking Neural Network framework
Stars: ✭ 60 (-97.15%)
mlp-gpt-jaxA GPT, made only of MLPs, in Jax
Stars: ✭ 53 (-97.49%)
AdvPCAdvPC: Transferable Adversarial Perturbations on 3D Point Clouds (ECCV 2020)
Stars: ✭ 35 (-98.34%)
POPQORNAn Algorithm to Quantify Robustness of Recurrent Neural Networks
Stars: ✭ 44 (-97.91%)
geometric advGeometric Adversarial Attacks and Defenses on 3D Point Clouds (3DV 2021)
Stars: ✭ 20 (-99.05%)
SimP-GCNImplementation of the WSDM 2021 paper "Node Similarity Preserving Graph Convolutional Networks"
Stars: ✭ 43 (-97.96%)
jax-modelsUnofficial JAX implementations of deep learning research papers
Stars: ✭ 108 (-94.88%)
jax-cfdComputational Fluid Dynamics in JAX
Stars: ✭ 399 (-81.07%)
Pro-GNNImplementation of the KDD 2020 paper "Graph Structure Learning for Robust Graph Neural Networks"
Stars: ✭ 202 (-90.42%)
jax-rlJAX implementations of core Deep RL algorithms
Stars: ✭ 61 (-97.11%)
ADAMADAM implements a collection of algorithms for calculating rigid-body dynamics in Jax, CasADi, PyTorch, and Numpy.
Stars: ✭ 51 (-97.58%)
grbGraph Robustness Benchmark: A scalable, unified, modular, and reproducible benchmark for evaluating the adversarial robustness of Graph Machine Learning.
Stars: ✭ 70 (-96.68%)
omdJAX code for the paper "Control-Oriented Model-Based Reinforcement Learning with Implicit Differentiation"
Stars: ✭ 43 (-97.96%)
pre-trainingPre-Training Buys Better Robustness and Uncertainty Estimates (ICML 2019)
Stars: ✭ 90 (-95.73%)
FGSM-KerasImplemention of Fast Gradient Sign Method for generating adversarial examples in Keras
Stars: ✭ 43 (-97.96%)
graphsignalGraphsignal Python agent
Stars: ✭ 158 (-92.5%)
EinopsDeep learning operations reinvented (for pytorch, tensorflow, jax and others)
Stars: ✭ 4,022 (+90.8%)
Thinc🔮 A refreshing functional take on deep learning, compatible with your favorite libraries
Stars: ✭ 2,422 (+14.9%)
JaxComposable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Stars: ✭ 15,579 (+639.04%)
DatasetsTFDS is a collection of datasets ready to use with TensorFlow, Jax, ...
Stars: ✭ 3,094 (+46.77%)