VERIFAI - A Step Towards Evaluating the Responsibility of AI-Systems

Abstract

This work represents the first step towards a unified framework for evaluating an AI system's responsibility by building a prototype application.The python based web-application uses several libraries for testing the fairness, robustness, privacy, and explainability of a machine-learning model as well as the dataset which was used for training the model.The workflow of the prototype is tested and described using images of a healthcare dataset since healthcare represents an area where automatic decisions affect decisions about human lives, and building responsible AI in this area is therefore indispensable.