Securely access open source trusted AI packages in IBM Cloud Pak for Data
Access Access AI Fairness 360, AI Explainability 360 Toolkit, and the Adversarial Robustness Toolbox
As open source artificial intelligence technologies grow, the need for AI systems to make decisions fairly, to be invulnerable to tampering, and to be explainable is more important than ever. At IBM, we believe that building trust in AI starts in the open, with code that is transparent and accessible to anyone. To support our commitment to trusted AI, IBM previously released 3 open source trusted AI packages: AI Fairness 360, AI Explainability 360, and the Adversarial Robustness Toolbox.
Developers need to incorporate trust in data and models as well as in the way packages are used inside their projects, so they don’t end up using packages with vulnerabilities or legal implications. In the latest IBM Cloud Pak for Data release, we added a feature to give developers secure access to our trusted AI packages via IBM Cloud Pak for Data’s Open Source Management service.
Let’s take a closer look at the trusted AI packages and how to access them in IBM Cloud Pak for Data.
Trusted AI packages
- AI Fairness 360 Toolkit (AIF360): Available in both Python and R, the AI Fairness 360 package includes a comprehensive set of metrics (over 70) for datasets and models to test for biases, explanations for these metrics, and algorithms (about 11) to mitigate bias in datasets and models. AIF360 translates algorithmic research from the lab into the actual practice of domains as wide-ranging as finance, human capital management, healthcare, and education. Find guidancefor using the tool.
- AI Explainability 360 Toolkit (AIX360): An open source library that supports interpretability and explainability of datasets and machine learning models throughout the AI application lifecycle. The AI Explainability 360 Python package includes a comprehensive set of algorithms that cover different dimensions of explanations along with proxy explainability metrics. Find guidance for using the tool.
- Adversarial Robustness Toolbox (ART): A Python library supporting developers and researchers in defending machine learning models against adversarial threats (including evasion, extraction and poisoning) and helps making AI systems more secure and trustworthy. ART includes attacks for testing defenses with state-of-the-art threat models. Find tutorials about notebooks and examples for using the tool.
Users of IBM Cloud Pak for Data can take advantage of these packages via the Open Source Management service within the product.
Using trusted AI packages in the Open Source Management service
In May, IBM announced the availability of the Open Source Management (OSM) service in Cloud Pak for Data 3.0. The service provides access to a curated list of 800 pre-approved open source packages and walks you through a governed workflow to request adding a new package offering insights to security and vulnerability risks. The result is that you’re better able to understand what open source packages are used the most, who in your organization is using the packages, and vulnerabilities related to each project.
You can now use the Open Source Management service to access the trusted AI packages.
See how to access the tools
Now that you know what they are, let’s look at how you access the packages via IBM Cloud Pak for Data.
Once you’re logged into IBM Cloud Pak for Data, enable and open
Open Source Management service. Select Open source packages to see a list of the pre-approved packages, including the trusted AI packages.
Click on the package tile to get information about the package summary, license, source link and installation guide (under attachments), usage details, rating, and review.
To link to a project, click on
Link to projects. Select the project where you need to use the package.
Now developers can safely install and use the approved packages in the project.
Users can also initiate requests to add new package to the OSM-approved list in case it is not available in the already existing list of packages.
Find granular data about your open source packages
To help you better manage your open source consumption, the Open Source Management services gives you a holistic view of data related to projects’ use of open source packages, license usage, vulnerability reports, user interactions with open source packages, and most active users.
An admin can also approve package request from the developers.