Join Our Community
Connect with researchers, practitioners, and enthusiasts passionate about AI safety.
Meet the team
The people driving AI Safety for Italy forward.
Valeriia Povergo
Organizing Team — Operations & Governance
Valeriia is part of the organizing group of AI Safety for Italy, contributing to the coordination and development of the initiative across governance, finance, communications, and operational support. Her background is primarily in operations, project coordination, stakeholder relationship development, and fundraising across international initiatives and campaigns. She has experience supporting organizational processes, cross-functional coordination, and the development of operational infrastructure. Her recent involvement in AI safety includes participation in initiatives such as AI Safety Camp, Apart Research, and the Corda Democracy Fellowship.
Carola Caivano
Organizing Team — Communications & Community
Carola is part of the organizing group of AI Safety for Italy, contributing to the development of the initiative across external communications, community strategy, and networking. Her background is in physics and she currently works as a data scientist. Her involvement in AI safety includes participating in the ML4Good bootcamp and graduating from BlueDot Impact’s AI Alignment course.
Elisabetta Rocchetti
Co-founding Collaborator — PhD Candidate
Elisabetta is a co-founding collaborator of AI Safety for Italy and a PhD candidate in Computer Science at Università degli Studi di Milano, where her research focuses on mechanistic interpretability. Her work spans refusal behaviour, instruction-following mechanisms, training dynamics, and the encoding of aesthetic concepts, using methods such as activation patching, steering, probing, and complex network modeling.
Cristian Curaba
Technical Infrastructure & Didactics
Cristian holds a Master’s degree in Data Science and Scientific Computing and a Bachelor’s in Mathematics, providing him with a rigorous analytical and problem-solving foundation. He actively participated in the Apart Fellowship, ML4Good France, and various related courses. His involvement extends to local community building, where he currently leads an AGI Safety Discussion Group at the University of Udine to engage researchers and students in critical AI safety topics.
Francesco Ortu
Co-founder — PhD Student
Francesco is a co-founder of AI Safety for Italy and a PhD student at the University of Trieste and Area Science Park. His research focuses on the mechanistic interpretability of LLMs and VLMs. As part of his PhD, he visited the AI Safety and Alignment group at the ELLIS Institute in Tübingen.
Luca Scionis
PhD Student
Luca Scionis is a PhD student in the Italian National AI PhD Programme, affiliated with the University of Cagliari (sAIferLab). He is currently an ELLIS intern working on the AI safety of AI agents. His research spans adversarial machine learning, with a focus on the robustness of computer vision models, and AI safety, particularly the security of LLM-based agents and assistants.
Community Members
Last updated: 2026-06-30
| Name | Location | Areas of Interest |
|---|---|---|
|
A
Angelo Leone
|
Londra, Regno Unito | Evaluation (capability evaluations, dangerous capability evals, benchmarking), Alignment (RLHF, scalable oversight, value alignment), AI governance e policy, Etica dell'AI e impatto sociale |
|
L
Luca Mattiazzi
|
Milano, Italia | Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Evaluation (capability evaluations, dangerous capability evals, benchmarking), Alignment (RLHF, scalable oversight, value alignment), Sicurezza informatica per modelli di frontiera |
|
C
Cristian Curaba
|
Udine, Italia | Monitoraggio attraverso metodi formali |
|
M
Madhusudhan Pathak
|
Padova, Italy | Alignment (RLHF, scalable oversight, value alignment), Etica dell'AI e impatto sociale |
|
L
Lorenzo Pacchiardi
|
Cambridge, United Kingdom | Evaluation (capability evaluations, dangerous capability evals, benchmarking), Alignment (RLHF, scalable oversight, value alignment), AI governance e policy, Rischi catastrofici / esistenziali |
|
R
Raffaele Mura
|
Cagliari, Italia | Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Robustness e adversarial ML, AI governance e policy, Sicurezza informatica per modelli di frontiera |
|
G
Giulia Consonni
|
Neustadt (Weinstr.), Germania | Rischi catastrofici / esistenziali, AI safety communications |
|
L
Luca Scionis
|
Cagliari, Italia | Evaluation (capability evaluations, dangerous capability evals, benchmarking), Robustness e adversarial ML |
| Bologna, Italia | Evaluation (capability evaluations, dangerous capability evals, benchmarking), Alignment (RLHF, scalable oversight, value alignment), Robustness e adversarial ML, Rischi catastrofici / esistenziali | |
|
C
Carola Maria Caivano
|
Torino, Italia | Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Evaluation (capability evaluations, dangerous capability evals, benchmarking), AI governance e policy, Etica dell'AI e impatto sociale |
|
B
Battista Biggio
|
Cagliari, Italia | Interpretability (mechanistic interpretability, analisi delle rappresentazioni, ecc.), Robustness e adversarial ML |
Want to be part of this list?
Fill in our interest form to join AI Safety for Italy.
Join the communityReady to Join Our Community?
Whether you're a researcher, student, professional, or simply curious about AI safety, there's a place for you in our community.
Join the Community