Trustworthy Property Enforcement in Data-Driven AI: Application to Agentic Systems
Posted on: 18/03/2026
Deadline: 04/04/2026
Scientific-Disciplinary Group
09/IINF-05 - Information Processing Systems
Description
The research project aims to address the growing need to develop artificial intelligence systems that are not only highly performant, but also safe, reliable, and compliant with emerging regulatory frameworks governing their deployment, including the EU AI Act. The research activity focuses on the design of hybrid methodologies that integrate machine learning techniques with symbolic approaches and mathematical optimization tools, in order to guarantee the satisfaction of formal properties such as correctness, robustness, fairness, and verifiability in data-driven AI systems. The goal is to overcome the limitations of purely statistical models by introducing formally grounded mechanisms for control and validation.
Job posting website
Funding body
ALMA MATER STUDIORUM - UNIVERSITA' DI BOLOGNA - - DIPARTIMENTO DI INFORMATICA - SCIENZA E INGEGNERIA
How to apply
Other
Selection process
Click to expand
View the original posting on the MUR website: Go to MUR website