# Hardened Extension of the Adversarial Robustness Toolbox (HEART)
![Static Badge](https://img.shields.io/badge/python-3.9%20--%203.10-blue "Python 3.9 - 3.10 version support.")
HEART is a Python extension library for Machine Learning Security that builds on the popular Adversarial Robustness algorithms within the [Adversarial Robustness Toolbox (ART)](https://github.com/Trusted-AI/adversarial-robustness-toolbox). The extension library allows the user to leverage core ART algorithms while providing additional benefits to AI Test & Evaluation (T&E) engineers.
- Support for T&E of models for Department of Defense use cases
- Alignment to [MAITE](https://github.com/mit-ll-ai-technology/maite) protocols for seamless T&E workflows
- Essential subset of adversarial robustness methods for targeted AI security coverage
- Quality assurance of model assessments in the form of metadata
- In-depth support for users based on codified T&E expert experience in form of guides and examples
- Front-end application for low-code users: HEART Gradio Application
# Installation
### From Python Packaging Index (PyPI)
To install the latest version of HEART from PyPI, run:
```shell
pip install heart-library
```
### From IBM GitHub Source
To install the latest version of HEART from the [heart-library public GitHub](https://github.com/IBM/heart-library), run:
```shell
git clone https://github.com/IBM/heart-library.git
cd heart-library
pip install .
```
### (Optional) Development Environment via Poetry
In some cases, it may be beneficial for developers to set up an environment from a reproducible source of truth. This environment is useful for developers that wish to work within a pull request or leverage the same development conditions used by HEART contributors. Please follow the instructions for installation via Poetry within the official HEART repository:
- [Poetry Installation Instructions](https://github.com/IBM/heart-library/blob/main/poetry_installation.md)
# Getting Started With HEART
IBM has published a catalog of notebooks designed to assist developers of all skill levels with the process of getting started utilizing HEART in their AI T&E workflows. These Jupyter notebooks can be accessed within the official heart-library GitHub repository:
- [HEART Jupyter Notebooks](https://github.com/IBM/heart-library/tree/main/notebooks)
# HEART Modules
The HEART library is organized into three primary modules: attacks, estimators, and metrics.
### heart_library.attacks
> The HEART attacks module contains implementations of attack algorithms for generating adversarial examples and evaluating model robustness.
### heart_library.estimators
> The HEART estimators module contains classes that wrap and extend the evaluated model to make it compatible with attacks and metrics.
### heart_library.metrics
> The HEART metrics module implements industry standard, commonly-used T&E metrics for model evaluation.
Raw data
{
"_id": null,
"home_page": "https://github.com/IBM/heart-library",
"name": "heart-library",
"maintainer": null,
"docs_url": null,
"requires_python": "<3.11,>=3.9",
"maintainer_email": null,
"keywords": "machine learning, adversarial ai, evasion",
"author": "Mark Baker, Jordan Fischer, Kieran Fraser, Jackson Lee, Adam Lockwood",
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/6b/c6/cb585cadb0356ef9e4cb85131742efe596aa9e30e2ed422cec4a5aa82269/heart_library-0.3.1.tar.gz",
"platform": null,
"description": "# Hardened Extension of the Adversarial Robustness Toolbox (HEART) \n\n![Static Badge](https://img.shields.io/badge/python-3.9%20--%203.10-blue \"Python 3.9 - 3.10 version support.\")\n\nHEART is a Python extension library for Machine Learning Security that builds on the popular Adversarial Robustness algorithms within the [Adversarial Robustness Toolbox (ART)](https://github.com/Trusted-AI/adversarial-robustness-toolbox). The extension library allows the user to leverage core ART algorithms while providing additional benefits to AI Test & Evaluation (T&E) engineers.\n\n- Support for T&E of models for Department of Defense use cases \n- Alignment to [MAITE](https://github.com/mit-ll-ai-technology/maite) protocols for seamless T&E workflows\n- Essential subset of adversarial robustness methods for targeted AI security coverage \n- Quality assurance of model assessments in the form of metadata \n- In-depth support for users based on codified T&E expert experience in form of guides and examples\n- Front-end application for low-code users: HEART Gradio Application \n\n# Installation\n\n### From Python Packaging Index (PyPI)\n\nTo install the latest version of HEART from PyPI, run:\n\n```shell\npip install heart-library\n```\n\n### From IBM GitHub Source\n\nTo install the latest version of HEART from the [heart-library public GitHub](https://github.com/IBM/heart-library), run:\n\n```shell\ngit clone https://github.com/IBM/heart-library.git\ncd heart-library\npip install .\n```\n\n### (Optional) Development Environment via Poetry\n\nIn some cases, it may be beneficial for developers to set up an environment from a reproducible source of truth. This environment is useful for developers that wish to work within a pull request or leverage the same development conditions used by HEART contributors. Please follow the instructions for installation via Poetry within the official HEART repository:\n\n- [Poetry Installation Instructions](https://github.com/IBM/heart-library/blob/main/poetry_installation.md)\n\n# Getting Started With HEART\n\nIBM has published a catalog of notebooks designed to assist developers of all skill levels with the process of getting started utilizing HEART in their AI T&E workflows. These Jupyter notebooks can be accessed within the official heart-library GitHub repository:\n\n- [HEART Jupyter Notebooks](https://github.com/IBM/heart-library/tree/main/notebooks)\n\n# HEART Modules\n\nThe HEART library is organized into three primary modules: attacks, estimators, and metrics.\n\n### heart_library.attacks\n\n> The HEART attacks module contains implementations of attack algorithms for generating adversarial examples and evaluating model robustness.\n\n### heart_library.estimators\n\n> The HEART estimators module contains classes that wrap and extend the evaluated model to make it compatible with attacks and metrics.\n\n### heart_library.metrics\n\n> The HEART metrics module implements industry standard, commonly-used T&E metrics for model evaluation.\n\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Hardened Extension of the Adversarial Robustness Toolbox (HEART) supports assessment of adversarial AI vulnerabilities in Test & Evaluation workflows.",
"version": "0.3.1",
"project_urls": {
"Homepage": "https://github.com/IBM/heart-library",
"Repository": "https://github.com/IBM/heart-library"
},
"split_keywords": [
"machine learning",
" adversarial ai",
" evasion"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "f560802b5cf4ff9025474a0cf252683a8619c8d188c06501bf70c3475cc825dd",
"md5": "ab9fa4398d4e19ef7b20dc3d3b9df4c6",
"sha256": "df86e73d9e24e773e80d73915b0375a45ec59a8c3df60ce0a8c2acf4006ac367"
},
"downloads": -1,
"filename": "heart_library-0.3.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "ab9fa4398d4e19ef7b20dc3d3b9df4c6",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<3.11,>=3.9",
"size": 28856,
"upload_time": "2024-04-15T18:33:03",
"upload_time_iso_8601": "2024-04-15T18:33:03.943481Z",
"url": "https://files.pythonhosted.org/packages/f5/60/802b5cf4ff9025474a0cf252683a8619c8d188c06501bf70c3475cc825dd/heart_library-0.3.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "6bc6cb585cadb0356ef9e4cb85131742efe596aa9e30e2ed422cec4a5aa82269",
"md5": "ec20bc77991cfd52e46782eac6620025",
"sha256": "f34138f82c9222774dee1ff87ad7f452968c7de4b928887bf5d1ee7f41752ca1"
},
"downloads": -1,
"filename": "heart_library-0.3.1.tar.gz",
"has_sig": false,
"md5_digest": "ec20bc77991cfd52e46782eac6620025",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<3.11,>=3.9",
"size": 17434,
"upload_time": "2024-04-15T18:33:05",
"upload_time_iso_8601": "2024-04-15T18:33:05.810938Z",
"url": "https://files.pythonhosted.org/packages/6b/c6/cb585cadb0356ef9e4cb85131742efe596aa9e30e2ed422cec4a5aa82269/heart_library-0.3.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-04-15 18:33:05",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "IBM",
"github_project": "heart-library",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "heart-library"
}