TODO
Project description
.. raw:: html
<div align="center">
.. raw:: html
</div>
Intro
-----
**Toxic** is an open source software library for machine learning
security. It contains tools for adversarial example generation and
provides a framework for building new types of attack methods.
Currently in the dev stage.
Attacks
-------
Available attack algorithms implemented in Toxic:
- Fast Gradient Methods (FGM/FGSM)
```Tutorial`` </tutorial/source/fgsm.ipynb>`__
- Basic Iterative
```Tutorial`` </tutorial/source/basic_iterative.ipynb>`__
- Momentum Iterative
```Tutorial`` </tutorial/source/momentum_iterative.ipynb>`__
- DeepFool
- Universal Adversarial Perturbation (UAP)
- Jacobian-based Saliency Map Approach (JSMA)
- One Pixel Attack
- LBFGS
- Carlini Wagner L2
- Carlini Wagner L-inf
- Feature Adversaries
- Boundary Attack
- Elastic Net
- Natural Adversarial Examples (NAE)
The Team
~~~~~~~~
Toxic is a community driven project. The project was initiated by
machine learning security team @ `KakaoBrain <kakaobrain.com>`__.
.. |license| image:: https://img.shields.io/github/license/mashape/apistatus.svg
Project details
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
toxic-0.1.0.tar.gz
(17.3 kB
view hashes)
Built Distribution
toxic-0.1.0-py3-none-any.whl
(50.3 kB
view hashes)