AI Safety Connect Day - From quantitative risk modeling to safe-by-design AI research: ensuring AI technologies are safe

​​This session is part of AI Safety Connect Day (February 18, 2026, The Imperial Hotel, New Delhi) — a high-level, invitation-only side event co-hosted by AI Safety Connect and IASEAI. See our speakers and the full program, and register your interest for the main event here.

How do we move from identifying AI risks to actively designing safety into AI systems from the ground up? SaferAI presents an overview of their work on risk management, quantitative risk modeling, and the case for greater investment in a safe-by-design AI research agenda.

This presentation will draw on SaferAI's recent research:

• ​Toward Quantitative Modeling of Cybersecurity Risks Due to AI Misuse

• ​A Methodology for Quantitative AI Risk Modeling

• ​The Role of Risk Modeling in Advanced AI Risk Management

​Speakers:

• ​Dr. Chloé Touzet | Policy Lead, SaferAI

• ​Mr. Bruno Galizzi | Senior Policy Associate, SaferAI

​​Check the AI Safety Connect website for details on the live agenda for all our events.

Supported by
Minderoo Foundation, Sympatico Ventures, Future of Life Institute, and AISTOF.