diffai
by eth-sri
A certifiable defense against adversarial examples by training neural networks to be provably robust
AI summary
Robust network trainer
Trains neural networks to be provably robust against adversarial examples using abstract interpretation techniques.
- stars
- 219
- forks
- 26
- watching
- 16
Similar projects
Found by comparing what the projects do, not just their names.
Neural network trainer
A library for training and evaluating neural networks with a focus on adversarial robustness.
Network reprogramming
This project enables reprogramming of pre-trained neural networks to work on new tasks by fine-tuning them on smaller datasets.
Neural network reprogramming
Repurposes pre-trained neural networks for new classification tasks through adversarial reprogramming of their inputs.
Robustness framework
Provides a framework for computing tight certificates of adversarial robustness for randomly smoothed classifiers.
Robustness tester
A toolbox for researching and evaluating robustness against attacks on machine learning models
Robust Boosting Models
Provides provably robust machine learning models against adversarial attacks
Neural network optimizer
Trains artificial neural networks using the genetic algorithm
Training framework
A PyTorch framework for managing and automating deep learning training loops with features like hyperparameter tracking and single-file deployments.
GAN trainer
Improves GAN training efficiency by incorporating data augmentation
Training framework
A PyTorch-based neural network training framework with advanced features and utilities
Adversarial attacks library
PyTorch implementation of various Convolutional Neural Network adversarial attack techniques
Async neural network trainer
A distributed learning framework that enables peer-to-peer parameter averaging and asynchronous training of deep neural networks
Federated Learning Detector
Develops and evaluates a framework for detecting attacks on federated learning systems
Machine learning trainer
A Python implementation of a distributed machine learning framework for training neural networks on multiple GPUs
Neural network trainer
A Python library for training neural networks with focus on hydrological applications using PyTorch.
