Exploring privacy risk exposure by machine learning

Abstract

In recent years we are witnessing the diffusion of AI systems based on powerful machine learning models which find application in many critical contexts such as medicine, financial market, credit scoring, etc. In such contexts it is particularly important to design workflows for the learning of Trustworthy AI systems while guaranteeing interpretability of their decisional reasoning and privacy protection. In this talk we will explore the possible relationship between these two relevant ethical values to take into consideration in Trustworthy AI and how we can exploit machine learning for the assessment of privacy protection of data and (X)AI models.