Stars
Data from the paper "Risk-graded Safety for Handling Medical Queries in Conversational AI"
Spelling, grammar and style checking on LaTeX documents
Provable adversarial robustness at ImageNet scale
Code for our NeurIPS 2019 *spotlight* "Provably Robust Deep Learning via Adversarially Trained Smoothed Classifiers"
RobustBench: a standardized adversarial robustness benchmark [NeurIPS 2021 Benchmarks and Datasets Track]
Pytorch implementation of Bit-Flip based adversarial weight Attack (BFA)
Codes for NeurIPS 2020 paper "Adversarial Weight Perturbation Helps Robust Generalization"
PyTorch implementation of Near-Lossless Post-Training Quantization of Deep Neural Networks via a Piecewise Linear Approximation < E650 /p>
2.56%, 15.20%, 1.30% on CIFAR10, CIFAR100, and SVHN https://arxiv.org/abs/1708.04552
Best CIFAR-10, CIFAR-100 results with wide-residual networks using PyTorch
Unofficial implementation of the ImageNet, CIFAR 10 and SVHN Augmentation Policies learned by AutoAugment using pillow
Image augmentation for machine learning experiments.
Code snippets created for the PyTorch discussion board
Code relative to "Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks"
A pytorch adversarial library for attack and defense methods on images and graphs
A library for experimenting with, training and evaluating neural networks, with a focus on adversarial robustness.
TRADES (TRadeoff-inspired Adversarial DEfense via Surrogate-loss minimization)
astyonax / CFFI-numpy-openMP
Forked from nszceta/cffi-numpy-demoCFFI + Numpy + OpenMP -- a reference example
PyTorch Implementation of Adversarial Training for Free!
Code for ICML 2019 paper "Simple Black-box Adversarial Attacks"
PyTorch 1.0 implementation of the approximate Earth Mover's Distance
Dataset of around 800k images consisting of 1100 Famous Celebrities and an Unknown class to classify unknown faces
Reimplementation of Variational Inference with Normalizing Flows (https://arxiv.org/abs/1505.05770)
Implementations of various VAE-based semi-supervised and generative models in PyTorch
Tutorial on normalizing flows.