Library for simulating data poisoning attacks against online learning.
Project description
niteshade is a Python library for simulating data poisoning attack and defence strategies against online machine learning systems.
Repository Structure
Explanation of the various directories and files. Maybe some subsections?
Python API Documentation
For detailed documentation of the project and the Python API, visit https://oskarfernlund.github.io/niteshade/.
Releasing
Releases are published to PyPI and Conda-Forge automatically when a tag is pushed to GitHub.
# Set next version number
export RELEASE=x.x.x
# Create tags
git commit --allow-empty -m "Release $RELEASE"
git tag -a $RELEASE -m "Version $RELEASE"
# Push
git push --tags
Contributing
niteshade is an open-source project and collaboration is welcome.
email addresses.
Licensing
niteshade is an open-source project and collaboration is welcome.
email addresses.
Project details
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 niteshade-0.0.1-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | d2f47a47f21ba6d34f0793230a92c6d61994a5026279f302fbf50730fd38281e |
|
MD5 | d35b0ac4d02b573d7775b3368b40e008 |
|
BLAKE2b-256 | e37c2dc8a3103201f0feeeaab4a53e939a85c3098b06908c51434a1fdc98f6dd |