BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Is it even possible to defend AI agents against attacks in practic
 e? - Ilia Shumailov (AI Sequrity Company\, Ex DeepMind\, Ex Cambridge)
DTSTART:20251028T130000Z
DTEND:20251028T140000Z
UID:TALK239713@talks.cam.ac.uk
CONTACT:Mateja Jamnik
DESCRIPTION:Prompt injections make deployment of AI agents hard in practic
 e. In this talk I will cover the current status quo in agentic AI security
  and try predicting where the future will take us. \n\nBio: Ilia Shumailov
  holds a PhD in Computer Science from the University of Cambridge. Until r
 ecently Ilia was a Senior Research Scientist at Google DeepMind focusing o
 n the intersection of machine learning\, privacy\, and computer security. 
  At present Ilia runs a company sequrity.ai building tools to secure AI ag
 ents of the future. \n\n"You can also join us on Zoom":https://cam-ac-uk.z
 oom.us/j/83400335522?pwd=LkjYvMOvVpMbabOV1MVTm8QU6DrGN7.1
LOCATION:Computer Laboratory\, William Gates Building\, Room FW11 (note ch
 ange of room)
END:VEVENT
END:VCALENDAR