Ph.D. candidate in Ingegneria Informatica E Dei Sistemi , 38th cycle (2022-2025)
Department of Control and Computer Engineering (DAUIN)
Profile
PhD
Research topic
The decision-making process followed by machine learning models is often unobservable. For this reason, it is essential to develop methodologies that make this process more transparent.
Tutors
Research presentation
Keywords
Teaching
Teachings
Bachelor of Science
- Basi di dati. A.A. 2023/24, INGEGNERIA INFORMATICA. Collaboratore del corso
Research
Research groups
Publications
Latest publications View all publications in Porto@Iris
- De Felice, Giovanni; Casanova Flores, Arianna; De Santis, Francesco; Santini, Silvia; ... (In stampa)
Causally Reliable Concept Bottleneck Models. In: Advances in Neural Information Processing Systems
Contributo in Atti di Convegno (Proceeding) - De Santis, Francesco; Bich, Philippe; Ciravegna, Gabriele; Barbiero, Pietro; Cerquitelli ... (2026)
Towards Better Generalization and Interpretability in Unsupervised Concept-Based Models. In: European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD), Porto (PRT), September 15–19, 2025, pp. 478-494. ISBN: 978-3-032-06065-5
Contributo in Atti di Convegno (Proceeding) - De Santis, Francesco; Ciravegna, Gabriele; Bich, Philippe; Giordano, Danilo; ... (2026)
V-CEM: Bridging Performance and Intervenability in Concept-Based Models. In: 3rd World Conference on Explainable Artificial Intelligence, xAI 2025, Istanbul (TUR), July 9–11, 2025, pp. 48-67. ISSN 1865-0937. ISBN: 9783032083166
Contributo in Atti di Convegno (Proceeding) - De Santis, Francesco; Giordano, Danilo; Mellia, Marco (2026)
GLEm-Net: Unified framework for data reduction with categorical and numerical features. In: KNOWLEDGE-BASED SYSTEMS, vol. 334. ISSN 0950-7051
Contributo su Rivista - De Santis, Francesco; Huang, Kai; Valentim, Rodolfo; Giordano, Danilo; Mellia, Marco; ... (2025)
CFA-Bench: Cybersecurity Forensic Llm Agent Benchmark and Testing. In: 2025 IEEE European Symposium on Security and Privacy Workshops (EuroS&PW), Venice (ITA), 30 June - 04 July 2025, pp. 217-225. ISBN: 979-8-3315-9546-3
Contributo in Atti di Convegno (Proceeding)