robustness

Neural network trainer

A library for training and evaluating neural networks with a focus on adversarial robustness.

A library for experimenting with, training and evaluating neural networks, with a focus on adversarial robustness.

GitHub

918 stars
19 watching
181 forks
Language: Jupyter Notebook
last commit: 11 months ago

Related projects:

Repository Description Stars
eth-sri/diffai Trains neural networks to be provably robust against adversarial examples using abstract interpretation techniques. 218
neuralhydrology/neuralhydrology A Python library for training neural networks with focus on hydrological applications using PyTorch. 364
intelligent-machine-learning/dlrover An automatic distributed deep learning system that simplifies the training of large AI models 1,270
borealisai/advertorch A toolbox for researching and evaluating robustness against attacks on machine learning models 1,308
open-mmlab/mmengine Provides a flexible and configurable framework for training deep learning models with PyTorch. 1,179
wyy-123-xyy/ra-fed A Python implementation of a distributed machine learning framework for training neural networks on multiple GPUs 6
robustbench/robustbench A standardized benchmark for measuring the robustness of machine learning models against adversarial attacks 667
guanghelee/neurips19-certificates-of-robustness Tight certificates of adversarial robustness for randomly smoothed classifiers 17
jedld/brains-jruby An implementation of a feedforward neural network toolkit for JRuby 60
imistyrain/matconvnet-oneclick A tool to train and deploy convolutional neural networks in MATLAB using MatConvNet 87
ahmedfgad/neuralgenetic Tools and techniques for training neural networks using genetic algorithms 240
molcik/python-neuron A Python library for implementing and training various neural network architectures 40
loudinthecloud/dpwa A distributed learning framework that enables peer-to-peer parameter averaging and asynchronous training of deep neural networks 53
paarthneekhara/rnn_adversarial_reprogramming Repurposes pre-trained neural networks for new classification tasks through adversarial reprogramming of their inputs. 6
mikecmpbll/rann Provides objects and algorithms for designing, processing and training Artificial Neural Networks in Ruby. 3