Spaces:
Running
Running
Update README.md to include additional information about HEART
Browse files
README.md
CHANGED
|
@@ -10,4 +10,64 @@ pinned: false
|
|
| 10 |
license: mit
|
| 11 |
---
|
| 12 |
|
| 13 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 10 |
license: mit
|
| 11 |
---
|
| 12 |
|
| 13 |
+
# Hardened Extension of the Adversarial Robustness Toolbox (HEART)
|
| 14 |
+
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
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.
|
| 18 |
+
|
| 19 |
+
- Support for T&E of models for Department of Defense use cases
|
| 20 |
+
- Alignment to [MAITE](https://github.com/mit-ll-ai-technology/maite) protocols for seamless T&E workflows
|
| 21 |
+
- Essential subset of adversarial robustness methods for targeted AI security coverage
|
| 22 |
+
- Quality assurance of model assessments in the form of metadata
|
| 23 |
+
- In-depth support for users based on codified T&E expert experience in form of guides and examples
|
| 24 |
+
- Front-end application for low-code users: HEART Gradio Application
|
| 25 |
+
|
| 26 |
+
# Installation
|
| 27 |
+
|
| 28 |
+
### From Python Packaging Index (PyPI)
|
| 29 |
+
|
| 30 |
+
To install the latest version of HEART from PyPI, run:
|
| 31 |
+
|
| 32 |
+
```shell
|
| 33 |
+
pip install heart-library
|
| 34 |
+
```
|
| 35 |
+
|
| 36 |
+
### From IBM GitHub Source
|
| 37 |
+
|
| 38 |
+
To install the latest version of HEART from the [heart-library public GitHub](https://github.com/IBM/heart-library), run:
|
| 39 |
+
|
| 40 |
+
```shell
|
| 41 |
+
git clone https://github.com/IBM/heart-library.git
|
| 42 |
+
cd heart-library
|
| 43 |
+
pip install .
|
| 44 |
+
```
|
| 45 |
+
|
| 46 |
+
### (Optional) Development Environment via Poetry
|
| 47 |
+
|
| 48 |
+
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:
|
| 49 |
+
|
| 50 |
+
- [Poetry Installation Instructions](https://github.com/IBM/heart-library/blob/main/poetry_installation.md)
|
| 51 |
+
|
| 52 |
+
# Getting Started With HEART
|
| 53 |
+
|
| 54 |
+
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:
|
| 55 |
+
|
| 56 |
+
- [HEART Jupyter Notebooks](https://github.com/IBM/heart-library/tree/main/notebooks)
|
| 57 |
+
|
| 58 |
+
# HEART Modules
|
| 59 |
+
|
| 60 |
+
The HEART library is organized into three primary modules: attacks, estimators, and metrics.
|
| 61 |
+
|
| 62 |
+
### heart_library.attacks
|
| 63 |
+
|
| 64 |
+
> The HEART attacks module contains implementations of attack algorithms for generating adversarial examples and evaluating model robustness.
|
| 65 |
+
|
| 66 |
+
### heart_library.estimators
|
| 67 |
+
|
| 68 |
+
> The HEART estimators module contains classes that wrap and extend the evaluated model to make it compatible with attacks and metrics.
|
| 69 |
+
|
| 70 |
+
### heart_library.metrics
|
| 71 |
+
|
| 72 |
+
> The HEART metrics module implements industry standard, commonly-used T&E metrics for model evaluation.
|
| 73 |
+
|