AI Privacy Toolkit gets a boost on dataset assessment in latest release

3rd July, 2023

Authors CyberKit4SME, Maya Anderson and Abigail Goldsteen

IBM’s AI Privacy Toolkit is a set of open-source tools designed to help organizations build more trustworthy AI solutions. It bundles together several practical tools and techniques related to the privacy and compliance of AI models. The toolkit is designed to be used by model developers (like data scientists) as part of their existing ML pipelines. It is implemented as a Python library that can be used with different ML frameworks such as scikit-learn, PyTorch, and Keras.

In addition to the existing ML model anonymization and data minimization modules, AI Privacy Toolkit now also supports privacy risk assessment for synthetic datasets.

Distance based metrics using holdout data

Distance based metrics using holdout data.


For details, please see:

, ,