Responsible and Trustworthy AI
Date: 18 June 2026
Room: CB30B
Chairs: Tatiana Tommasi (PoliTo), Roberto Pellungrini (SNS), Francesco Spinnato (UNIPI)
Description
The Responsible and Trustworthy AI workshop focuses on the study and development of artificial intelligence systems designed to be transparent, fair, robust, and aligned with ethical and regulatory principles. It addresses methods and techniques to ensure reliability, interpretability, and control in AI systems, including in critical settings. Topics include fairness, explainability, safety, accountability, and AI governance, with particular attention to societal, legal, and regulatory implications.
Detailed Programme
Times show each contribution's presentation slot. An asterisk marks the presenting author when provided in the programme data.
| Time | ID | Contribution |
|---|---|---|
| 14:30-14:40 | #9 | Collective Ethical Learning in Multi-Agent Systems via Dynamic Interaction Graphs |
| 14:40-14:50 | #52 | Advancing Trustworthy AI through Argumentation, Constraints, and Learning in the SMARTK Project |
| 14:50-15:00 | #42 | Solution Weakness in Abstract Argumentation Frameworks |
| 15:00-15:10 | #121 | From Human Values to Runtime Assurance for Autonomous AI Systems: Trustworthy and Ethical Systems Engineering at GSSI |
| 15:10-15:20 | #136 | Human-in-the-Loop Identity Preservation in Dance Movement Therapy |
| 15:20-15:30 | #11 | Visual Grounding Models in Counterfactual Scenarios |
| 15:30-15:40 | #17 | A Law of Data Reconstruction for Random Features (and Beyond) |
| 15:40-15:50 | #109 | Black-Box AI in Medical Diagnosis: Ethics and Law in the Physician–Patient Relationship |
| 15:50-16:00 | #48 | Analyzing the Effect of Quantization on Adversarial Transferability in LLMs |
| 16:00-16:10 | #51 | Trust and Uncertainty in L-DINF: Towards Explainable Decision Making for Cooperative Agents |
| 16:10-16:20 | #63 | DALI2: Trustworthy Neuro-Symbolic Agents via Logic-Based Governance of LLM Integration |
| 16:20-16:30 | #133 | Reliable and Trustworthy Artificial Intelligence at the PICUS Lab |
| 16:30-17:00 | Coffee Break | |
| 17:00-17:10 | #53 | A Neurosymbolic Approach for Landslide Risk Assessment |
| 17:10-17:20 | #59 | Verifying Reinforcement Learning Policies |