Python Trusted-ai Resources

Falcon signed sessions This project allows you to easily add trusted cookies to falcon, it works by storing a signed cookie in the client's browser us

AI Fairness 360 (AIF360) The AI Fairness 360 toolkit is an extensible open-source library containg techniques developed by the research community to h

This is a partial and quick and dirty proof of concept implementation of the following specifications to configure a tor client to use trusted exit re

A sentence search engine that fetches examples from trusted news/media websites. Great for improving writing & speaking better English.

Adversarial Robustness Toolbox (ART) is a Python library for Machine Learning Security. ART provides tools that enable developers and researchers to defend and evaluate Machine Learning models and applications against the adversarial threats of Evasion, Poisoning, Extraction, and Inference. ART supports all popular machine learning frameworks (TensorFlow, Keras, PyTorch, MXNet, scikit-learn, XGBoost, LightGBM, CatBoost, GPy, etc.), all data types (images, tables, audio, video, etc.) and machine learning tasks (classification, object detection, speech recognition, generation, certification, etc.).

UQ360 The Uncertainty Quantification 360 (UQ360) toolkit is an open-source Python package that provides a diverse set of algorithms to quantify uncert

UQ360 The Uncertainty Quantification 360 (UQ360) toolkit is an open-source Python package that provides a diverse set of algorithms to quantify uncert

AI Explainability 360 (v0.2.1) The AI Explainability 360 toolkit is an open-source library that supports interpretability and explainability of datase

This open source project serves two purposes. Collection and evaluation of a Question Answering dataset to improve existing QA/search methods - COVID-

ItsDangerous ... so better sign this Various helpers to pass data to untrusted environments and to get it back safe and sound. Data is cryptographical