robustness
by MadryLab
A library for experimenting with, training and evaluating neural networks, with a focus on adversarial robustness.
AI summary
Neural network trainer
A library for training and evaluating neural networks with a focus on adversarial robustness.
- stars
- 921
- forks
- 182
- watching
- 19
Similar projects
Found by comparing what the projects do, not just their names.
Robust network trainer
Trains neural networks to be provably robust against adversarial examples using abstract interpretation techniques.
Neural network trainer
A Python library for training neural networks with focus on hydrological applications using PyTorch.
Distributed Training System
Automates large-scale deep learning training on distributed clusters, providing fault tolerance and fast recovery from failures.
Robustness tester
A toolbox for researching and evaluating robustness against attacks on machine learning models
Deep learning trainer
Provides a flexible and configurable framework for training deep learning models with PyTorch.
Machine learning trainer
A Python implementation of a distributed machine learning framework for training neural networks on multiple GPUs
Adversarial benchmarking tool
A standardized benchmark for measuring the robustness of machine learning models against adversarial attacks
Robustness framework
Provides a framework for computing tight certificates of adversarial robustness for randomly smoothed classifiers.
Neural network library
An implementation of a feedforward neural network toolkit for JRuby
CNN trainer
A tool to train and deploy convolutional neural networks in MATLAB using MatConvNet
Neural network optimizer
Trains artificial neural networks using the genetic algorithm
Neural Network Library
A Python library for implementing and training various neural network architectures
Async neural network trainer
A distributed learning framework that enables peer-to-peer parameter averaging and asynchronous training of deep neural networks
Neural network reprogramming
Repurposes pre-trained neural networks for new classification tasks through adversarial reprogramming of their inputs.
Neural network library
Provides objects and algorithms for designing, processing and training Artificial Neural Networks in Ruby.
