neurips19-certificates-of-robustness
by guanghelee
"Tight Certificates of Adversarial Robustness for Randomly Smoothed Classifiers" (NeurIPS 2019, previously called "A Stratified Approach to Robustness for Randomly Smoothed Classifiers")
AI summary
Robustness framework
Provides a framework for computing tight certificates of adversarial robustness for randomly smoothed classifiers.
- stars
- 17
- forks
- 1
- watching
- 3
- awesome list
- 1
Similar projects
Found by comparing what the projects do, not just their names.
Model robustness testing
Evaluates and benchmarks the robustness of deep learning models to various corruptions and perturbations in computer vision tasks.
Robustness tester
A toolbox for researching and evaluating robustness against attacks on machine learning models
Adversarial benchmarking tool
A standardized benchmark for measuring the robustness of machine learning models against adversarial attacks
Robust Boosting Models
Provides provably robust machine learning models against adversarial attacks
Robust network trainer
Trains neural networks to be provably robust against adversarial examples using abstract interpretation techniques.
Adversarial testing tool
A Python toolkit for generating adversarial examples to test the robustness of natural language processing models
Segmentation robustness tool
Improving semantic segmentation robustness to motion blur using custom data augmentation techniques
Graph robustness toolkit
A toolbox for graph reliability and robustness against noise, distribution shifts, and attacks.
Neural network trainer
A library for training and evaluating neural networks with a focus on adversarial robustness.
Robust decision trees
An implementation of robust decision tree based models against adversarial examples using the XGBoost framework.
Model Robustness Tool
A toolset to evaluate the robustness of machine learning models
Fairness experiments
A framework for experimenting with robust optimization methods to improve fairness in machine learning models on noisy protected groups.
Robustness Sharing
An implementation of Federated Robustness Propagation in PyTorch to share robustness across heterogeneous federated learning users.
Noisy label toolkit
A Python package for robust inference via generative classifiers for handling noisy labels in machine learning.
Robust text model
A pre-trained Chinese language model designed to be robust against maliciously crafted texts
Featured in 1 awesome list
Each link jumps to the spot where the list mentions neurips19-certificates-of-robustness.
