BEGIN:VCALENDAR
VERSION:2.0
CALSCALE:GREGORIAN
PRODID:adamgibbons/ics
METHOD:PUBLISH
X-PUBLISHED-TTL:PT1H
BEGIN:VEVENT
UID:lzrB7BRwh_YNayM_d3mCO
SUMMARY:Lessons from the bleeding edge of AI/ML security
DTSTAMP:20260430T144232Z
DTSTART:20260522T092500Z
DESCRIPTION:Description:\nLarge Language Models have moved from research cu
	riosity to production reality at a pace that has left security teams scram
	bling. Organizations are racing to integrate LLMs into agentic browsers\, 
	AI-integrated development environments\, customer service chatbots\, and i
	nternal knowledge systems <b>–</b> often without fully understanding the n
	ovel attack surfaces they're introducing.\n\nThis talk examines security c
	hallenges at the frontier of LLM adoption: Prompt injection attacks turnin
	g helpful assistants into unwitting accomplices\, data exfiltration risks 
	hiding within conversational interfaces\, and the dangers of giving AI age
	nts the ability to take real-world actions on behalf of users. Drawing fro
	m academic research\, real-world implementations\, and documented incident
	s\, this talk will discuss what's working\, what's failing\, and what comp
	anies need to understand as these systems become embedded in critical work
	flows.\n--------------------------------\n\nSpeaker:\n- Keith Hoodlet\n\n-
	-------------------------------\n\nTalk details:\n- Link to the Big Techda
	y website: https://bigtechday.com/en/talks#6mEhk9SpfhzKaRIDmlhAZi\n
LOCATION:Kleine Lokhalle
DURATION:PT50M
END:VEVENT
END:VCALENDAR