/adversarial-robustness-toolbox

Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference

Primary LanguagePythonMIT LicenseMIT

Adversarial Robustness Toolbox (ART) v1.3


Build Status Documentation Status GitHub version Language grade: Python Total alerts codecov Code style: black License: MIT PyPI - Python Version slack-img

中文README请按此处

Adversarial Robustness Toolbox (ART) is a Python library for Machine Learning Security. ART provides tools that enable developers and researchers to evaluate, defend, certify and verify Machine Learning models and applications against the adversarial threats of Evasion, Poisoning, Extraction, and Inference. ART supports all popular machine learning frameworks (TensorFlow, Keras, PyTorch, MXNet, scikit-learn, XGBoost, LightGBM, CatBoost, GPy, etc.), all data types (images, tables, audio, video, etc.) and machine learning tasks (classification, object detection, generation, certification, etc.).


Learn more

Get Started Documentation Contributing
- Installation
- Examples
- Notebooks
- Attacks
- Defences
- Estimators
- Metrics
- Technical Documentation
- Slack, Invitation
- Contributing
- Roadmap
- Citing

The library is under continuous development. Feedback, bug reports and contributions are very welcome!