Abstract

The research studies the types of bias in the use of data in AI, analyses the risks of technologies based on AI and discusses the criteria for a transparent and reliable AI. 

Key words

Bias, Risk, Artificial Intelligence, algorithms, transparency

Publications and ongoing projects

PRIN 2020 BRIO – Bias, Risk, Opacity in AI (Project n. 2020SSKZ7R)
https://sites.unimi.it/brio/

• G. C. M. Amaral, T. P. Sales, G. Guizzardi, D. Porello. Towards a Reference Ontology of Trust. On the move to meaningful Internet Systems (OTM 2019). Rhodes, Greece, October 21-25. Lecture Notes in Computer Science 11877. 3-21.  2019.
• R. Confalonieri, P. Galliani, O. Kutz, D. Porello, G. Righetti, N. Troquard. Towards Knowledge-driven Distillation and Explanation of Black-box Models. In Proceedings of the Workshop on Data meets Applied Ontologies in Explainable AI (DAO-XAI 2021) part of Bratislava Knowledge September (BAKS 2021), Bratislava, Slovakia, September 18th to 19th, 2021. CEUR Workshop Proceedings 2998. 2021.
• Glenda C. M. Amaral, Daniele Porello, Tiago Prince Sales, Giancarlo Guizzardi. Modeling the Emergence of Value and Risk in Game Theoretical Approaches. In Advances in Enterprise Engineering XIV - 10th Enterprise Engineering Working Conference, EEWC 2020, Bozen-Bolzano, Italy, September 28, October 19, and November 9-10, 2020, Revised Selected Papers. Lecture Notes in Business Information Processing 411, Springer 2021

Departments

Department of Antiquities, Philosophy and History

Contacts

Prof. Daniele Porello (daniele.porello@unige.it)