May 1, 2021

515 words 3 mins read



a CLI that provides a generic automation layer for assessing the security of ML models

repo name Azure/counterfit
repo link
language Python
size (curr.) 158087 kB
stars (curr.) 266
created 2021-04-27
license MIT License


About | Getting Started | Learn More | Acknowledgments | Contributing | Trademarks | Contact Us

                          __            _____ __
  _________  __  ______  / /____  _____/ __(_) /_
 / ___/ __ \/ / / / __ \/ __/ _ \/ ___/ /_/ / __/
/ /__/ /_/ / /_/ / / / / /_/  __/ /  / __/ / /
\___/\____/\__,_/_/ /_/\__/\___/_/  /_/ /_/\__/




Counterfit is a command-line tool and generic automation layer for assessing the security of machine learning systems.

Getting Started

Choose one of these methods to get started quickly:

For more information including alternative installation instructions, please visit our wiki.

Option 1: Deploy via Azure Shell

To run Counterfit from your browser

  1. Click the button below to initiate small resource deployment to your Azure account.

Deploy to Azure

  1. In the configuration blade, specify your subscription and resource group.
  2. In your Azure Shell, type the following, replacing RESOURCE_GROUP with the name of the resource group selected in the previous step.
az container exec --resource-group RESOURCE_GROUP --name counterfit --exec-command '/bin/bash'
  1. Within the container, launch Counterfit.

Option 2: Setup an Anaconda Python environment and install locally

  1. Install Anaconda Python and git.
  2. Clone this repository.
git clone
  1. Open an Anaconda shell and create a virtual environment and dependencies.
cd counterfit
conda create --yes -n counterfit python=3.7
conda activate counterfit
pip install -r requirements.txt
  1. Launch Counterfit.

Learn More

Visit our wiki for more detailed instructions on


Counterfit leverages excellent open source projects, including, Adversarial Robustness Toolbox and TextAttack.


This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit

When you submit a pull request, a CLA bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA.

This project has adopted the Microsoft Open Source Code of Conduct. For more information see the Code of Conduct FAQ or contact with any additional questions or comments.


This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft’s Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party’s policies.

Contact Us

For comments or questions about how to leverage Counterfit, please contact

comments powered by Disqus