AI Safety & Security Meetup
We are pleased to launch the first in a quarterly series of AI Safety and Security community meetups in London, co-organized by ARIA's Trust Everything, Everywhere and Meta Security Team.
Capacity is limited, please register to make sure you secure your spot. Know someone who should be there? Share this event page with them!
Schedule:
5:30 - 6:00pm - Arrival & Checkin
6:00 - 6:05pm - Welcome Intro: Aaron Zhao, Meta Security Team
6:10 - 6:25pm - Pushing the frontier of AI-enabled FM - Nora Ammann, Progamme Director of Safeguarded AI at ARIA
6:30 - 6:45pm - When Agents become Weapons: the AI Worm - Hannah Foerster, University of Cambridge, Chrysalia
6:50 - 7:05pm - Ilia Shumailov, Meta
7:10 - 8:00pm - Networking Food & Drinks
About ARIA: The Advanced Research + Invention Agency (ARIA) is a UK R&D funding agency created to unlock technological breakthroughs that benefit everyone. ARIA funds teams of scientists and engineers to pursue research at the edge of what is scientifically and technologically possible.
About Trust Everything, Everywhere: ARIA's opportunity space focused on building the trust infrastructure needed for an increasingly programmable, cyber-physical and agentic world. It is currently home to two programmes: Scaling Trust (£50m), enabling AI agents to securely coordinate, negotiate and verify with one another, and Safeguarded AI (£59m), using fleets of AI agents to model and formally verify critical systems.
About Meta: Meta builds AI at scale, from open models to its personal agent, Muse, and invests heavily in making agentic systems safe and secure. Its Superintelligence Labs research spans prompt-injection resistance, sandboxed agent runtimes, human-in-the-loop controls and open bug bounty programmes, and it shares this work openly with the wider security and safety community.