Open Source AI Tools

Bias Auditing & Fair ML Toolkit

A collection of Google research projects related to Federated Learning and Federated Analytics.

Code for the TCAV ML interpretability project

Attributing predictions made by the Inception network using the Integrated Gradients method

Securify v2.0

The Python Differential Privacy Library. Built on top of: https://github.com/google/differential-privacy

Interpret Community extends Interpret repository with additional interpretability techniques and utility functions to handle real-world datasets and workflows.

Toolbox for diagnosing bias in machine learning models

Tensorflow's Fairness Evaluation and Visualization Toolkit

Microsoft SEAL 4.X For Python

detect demographic differences in the output of machine learning models or other assessments

Fairness evaluation environment for machine learning