Introduction to AI Safety
Over the past decade, artificial intelligence (AI) has woven its way into the fabric of our daily lives, touching everything from personalized recommendations to medical diagnoses, recognition systems, and data analytics. AI has become so widespread that it is shaping how we interact with technology and each other. Yet, as AI's technical capabilities have surged forward, its ethical and regulatory framework has struggled to keep pace. This lag has given rise to a host of ethical dilemmas, from biased algorithms to privacy breaches and social manipulation. This talk offers an introduction to AI ethics and safety, covering key topics like data and model vulnerabilities, algorithmic bias, adversarial attacks, foundational models, and the role of emerging standards.
Students will gain insight into why AI safety matters, how it’s addressed in practice, and the crucial role developers play in building fair, secure and trustworthy systems.
Date and Time
Location
Hosts
Registration
- Date: 05 Jun 2025
- Time: 09:00 AM UTC to 11:00 AM UTC
-
Add Event to Calendar
- Viale dell'Università, 50
- Cesena, Emilia-Romagna
- Italy 47521
- Room Number: 2.2
- Click here for Map
Speakers
Gabriele Graffieti
Introduction to AI Safety
Biography:
Gabriele Graffieti is a Sr. Algorithm Engineer at Ambarella, focusing on research and development of machine learning models for autonomous driving. He was the Head of AI Research at AI for People, an international nonprofit organization focused on the ethical and sociological aspects of AI. Before that he was a researcher at the University of Bologna, focusing on generative AI and continual learning.
Email: