Title: BRIO: A Bias and Risk Assessment Tool for Fair ML Systems Giuseppe Primiero, University of Milan Join the meeting <https://teams.microsoft.com/l/meetup-join/19%3ameeting_ZWE1MDUyMWItM2Q2MC00O...> Abstract: Phenomena of bias by AI systems based on machine learning methods are well known, and largely discussed in the literature. A variety of tools are being developed to assess these undesirable behaviours. In this talk I present BRIO, a bias and risk assessment tool developed by MIRAI (https://mirai.systems). The tool is based on a combination of formal and statistical methods and works on the I/O data of a ML system remaining agnostic on the model itself. The result of the analysis is a set of all the features and combinations thereof that produce violations with respect to a given target distribution. These values can be fed into a risk function which computes an overall value weighting them on parameters such as size of the population and number of features involved, mapping naturally into notions of group and individual fairness. <https://arxiv.org/abs/2407.02191>Bio: Giuseppe Primiero is Professor of Logic with the Logic, Uncertainty, Computation and Information Lab (luci.unimi.it) in the Department of Philosophy at the University of Milan, Italy. He acts as Scientific Director for PHILTECH, Research Center for The Philosophy of Technology (https://philtech.unimi.it/) and as Programme Leader for the Master's Degree in Human-Centered AI (https://hcai.cdl.unimi.it/en). He is co-founder and Chief Research Officer of MIRAI (https://mirai.systems). Giuseppe works in the formal modeling and verification of multi-agent systems. His preferred tools are proof-systems, modal and computational logics. Giuseppe's formal research is applied to AI systems and their deployment for resolving issues of misinformation and disinformation online, as well as computable approaches to the evaluation of trustworthiness of information sources, bias and fairness. He is currently the Principal Investigator of the Projects “BRIO: Bias, Risk and Opacity in AI” (https://sites.unimi.it/brio), and "SMARTEST: Simulation of probabilistic systems for the age of the digital twin" (https://sites.unimi.it/smartest/) both funded by the Italian Ministry of University and Research. Full CV at https://work.unimi.it/chiedove/cv/giuseppe_primiero.pdf. Subscribe to future talk announcements: Anyone outside Bell Labs can receive talk announcements by subscribing to the mailing list. To subscribe, send an empty email with the subject line "Subscribe RAI" to daniele.quercia@polito.it<mailto:daniele.quercia@polito.it>