.. raw:: html
<div align="center">
.. raw:: html
</div>
Intro
-----
**Detox** 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 Detox:
- 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
~~~~~~~~
Detox 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
Metadata
Release files for dtox 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| dtox-0.1.0.tar.gz | 17.9 kB | Without provenance | Details for dtox-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| dtox-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for dtox-0.1.0-py3-none-any.whl |
Total release size: 44.5 kB
Release files / dtox-0.1.0.tar.gz
| Download URL | dtox-0.1.0.tar.gz |
|---|---|
| Size | 17.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
d397e724ea11eacceae9beb5b455a31e76161d7ba587198557974adabb40082a
|
|
BLAKE2b-256 checksum How to use checksums |
497f728694df3e0b43e033e6b0d239dc7ced976db5ff126b3c63c50a8c798276
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
Release files / dtox-0.1.0-py3-none-any.whl
| Download URL | dtox-0.1.0-py3-none-any.whl |
|---|---|
| Size | 26.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
a431e8c1c5cd3cd978e4b8ed6316df254b1c3838ead95d6edeb1d9c847f56393
|
|
BLAKE2b-256 checksum How to use checksums |
e32fc4a25c97b54fef13ba61e7b3a256fbb45576f4b0055a0b660144388ea7c6
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
Security for dtox 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.