Ph.D. candidate in Ingegneria Informatica E Dei Sistemi , 38th cycle (2022-2025)
Department of Control and Computer Engineering (DAUIN)
Adjunct lecturer/Adjunct instructor
Department of Control and Computer Engineering (DAUIN)
External Collaborator
Department of Control and Computer Engineering (DAUIN)
Profile
PhD
Thesis title
Responsible AI: From Principles to Industrial Practices. Fairness and Accountability in AI Systems: from training datasets to final outputs.
Research topic
Responsible AI: from principles to industrial practices
Tutors
Research presentation
Keywords
Biography
I study data fairness in order to promote a responsible development and use of ML/AI technologies, in order to reduce algorithmic discrimination. My research goal is to address the challenges of fairness and accountability in AI pipelines, specifically for tabular training datasets containing sensitive data.
Teaching
Teachings
Master of Science
- Sistemi informativi aziendali. A.A. 2026/27, INGEGNERIA GESTIONALE. Collaboratore del corso
- Data Ethics and Data Protection. A.A. 2025/26, DATA SCIENCE AND ENGINEERING. Collaboratore del corso
- Sistemi informativi aziendali. A.A. 2025/26, INGEGNERIA GESTIONALE. Collaboratore del corso
- Sistemi informativi aziendali. A.A. 2024/25, INGEGNERIA GESTIONALE. Collaboratore del corso
- Data Ethics and Data Protection. A.A. 2023/24, DATA SCIENCE AND ENGINEERING. Collaboratore del corso
- Sistemi informativi aziendali. A.A. 2023/24, INGEGNERIA GESTIONALE. Collaboratore del corso
Bachelor of Science
- Politica e tecnica (Grandi Sfide - Digitale). A.A. 2023/24, INGEGNERIA INFORMATICA. Collaboratore del corso
- Politica e tecnica (Grandi Sfide - Digitale). A.A. 2022/23, INGEGNERIA INFORMATICA. Collaboratore del corso
Research
Research Areas/Fields/Groups
Research projects
Projects funded by commercial contracts
- Agentic AI for Software Requirements Engineering: opportunities and challenges in the telecommunication sector, (2026-2026) - Responsabile Scientifico
Commercial Research
Publications
Latest publications View all publications in Porto@Iris
- Ullasci, Martina; Rondina, Marco; Coppola, Riccardo; Giobergia, Flavio; De Cesare, ... (In stampa)
Measuring Linguistic Bias in LLMs Across I.N.P.S. (Italian, Neapolitan, Parmesan and Sicilian) Dialect Corpora. In: FAIEMA 2026, L'Aquila (ITA), 09-11 September 2026
Contributo in Atti di Convegno (Proceeding) - Shkajoti, Xhoana; Ullasci, Martina; Rondina, Marco; Coppola, Riccardo; Vetro', Antonio; ... (In stampa)
Auditing Bias in AI-Based Hiring Systems: A Fairness Analysis of Nationality and Gender Discrimination. In: GoodIT '26: 6th International Conference on Information Technology for Social Good, Pisa (IT), 02-04 September 2026
Contributo in Atti di Convegno (Proceeding) - Ullasci, Martina; Rondina, Marco; Coppola, Riccardo; Vetro', Antonio (In stampa)
Gender bias and propagation of stereotypes in GenAI-assisted recruitment. In: ACM International Conference on the Foundations of Software Engineering (FSE) - 2nd Intersectionality and Software Engineering Workshop, Montreal (CA), 05-09/07/2026
Contributo in Atti di Convegno (Proceeding) - Rondina, Marco; Vetro', Antonio; De Martin, Juan Carlos; Bargis, Manuela; Elia, Gabriele (2026)
AI Agents and the Progressive Intermediation Between Users and Online Services: A Critical Analysis. In: FUTURE INTERNET, vol. 18. ISSN 1999-5903
Contributo su Rivista - Fantino, Giacomo; Rondina, Marco; Vetro', Antonio; De Martin, Juan Carlos (2026)
Code for: Quantifying Privacy Risks in Synthetic Data: A Study on Black-Box Membership Inference.
Altro