Publications

Testing software for non-discrimination: an updated and extended audit in the Italian car insurance domain

Marco Rondina, Antonio Vetro’, Riccardo Coppola, Oumaima Regragui, Alessandro Fabris, Gianmaria Silvello, Gian Antonio Susto, Juan Carlos De Martin

Published in 2nd International Conference on Frontiers of Artificial Intelligence, Ethics, and Multidisciplinary Applications; 1st - 2nd October 2024; Athens, Greece., 2024

Context. As software systems become more integrated into society’s infrastructure, the responsibility of software professionals to ensure compliance with various non-functional requirements increases. These requirements include security, safety, privacy, and, increasingly, non-discrimination. Motivation. Fairness in pricing algorithms grants equitable access to basic services without discriminating on the basis of protected... Read more

Download paper here

Facial Analysis Systems and Down Syndrome

Marco Rondina, Fabiana Vinci, Antonio Vetro', Juan Carlos De Martin

Published in European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2023) - 3rd Workshop on Bias and Fairness in AI (BIAS23). In press., 2023

The ethical, social and legal issues surrounding facial analysis technologies have been widely debated in recent years. Key critics have argued that these technologies can perpetuate bias and discrimination, particularly against marginalized groups. We contribute to this field by reporting on the limitations of facial analysis systems with the faces... Read more

Download paper here

Completeness of Datasets Documentation on ML/AI Repositories: An Empirical Investigation

Marco Rondina, Antonio Vetro’, Juan Carlos De Martin

Published in 22nd Portuguese Conference on Artificial Intelligence (EPIA 2023), 2023

ML/AI is the field of computer science and computer engineering that arguably received the most attention and funding over the last decade. Data is the key element of ML/AI, so it is becoming increasingly important to ensure that users are fully aware of the quality of the datasets that they... Read more

Download paper here

Designing Logic Tensor Networks for Visual Sudoku puzzle classification

Lia Morra, Alberto Azzari, Letizia Bergamasco, Marco Braga, Luigi Capogrosso, Federico Delrio, Giuseppe Di Giacomo, Simone Eiraudo, Giorgia Ghione, Rocce Giudice, Alkis Koudounas, Luca Piano, Daniele Cambrin Rege, Matteo Risso, Marco Rondina, Sebastian Alessandro, Marco Russo, Francesco Taioli, lorenzo Vaiani, Chiara Vercellino

Published in 17th International Workshop on Neural-Symbolic Learning and Reasoning (NeSy 2023), 2023

Given the increasing importance of the neurosymbolic (NeSy) approach in artificial intelligence, there is a growing interest in studying benchmarks specifically designed to emphasize the ability of AI systems to combine low-level representation learning with high-level symbolic reasoning. One such recent benchmark is Visual Sudoku Puzzle Classification, that combines visual... Read more