Toolbox for adversarial machine learning.
Project description
Adversarial Robustness Toolbox (ART) v1.3
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!
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for adversarial-robustness-toolbox-1.3.1.tar.gz
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | a5ed157b8e119abee41d2e3a4a7a72ee5878b7a43657918ac407558d5110b516 |
|
| MD5 | 4db1090e0d31febdd2e1bb8ef3ac7dd8 |
|
| BLAKE2b-256 | a00127ce30cff22fa3f3374343ced946ecb6780cc235fc99e3ecab33924fad92 |
Hashes for adversarial_robustness_toolbox-1.3.1-py3-none-any.whl
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | cc745048c6379b6102aee8533f27d2d9238aa72454920a2f2c82ecb894297f54 |
|
| MD5 | 1d7d1d05e35dc14a79c7297feb459bb2 |
|
| BLAKE2b-256 | fd75a219c7c9c745ef781dce3d8a9470f14a864272092ab6696b05c6deb7688a |
