BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//bsidesluxembourg-2026//talk//SDCESA
BEGIN:VTIMEZONE
TZID:CET
BEGIN:STANDARD
DTSTART:20001029T040000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000326T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-bsidesluxembourg-2026-SDCESA@pretalx.com
DTSTART;TZID=CET:20260508T141000
DTEND;TZID=CET:20260508T144000
DESCRIPTION:One of the top concerns in the age of AI is cyber attacks\, and
  one of the weak links in defense is AI itself. From prompt injections to 
 agents -self organizing into botnets or far worse\, we need some basic lev
 el of security for any AI workloads. And while we have seen a cohort of st
 artups being acquired in the space through 2025\, is the issue really solv
 ed? Does security for AI has to be yet another budget spend\, or can we do
  better with open source and open standards? We will discuss an open sourc
 e project\, AIDR bastion\, which was made inside our own SOC and released 
 to the world\, things which work and shortcomings. Goal of the talk is to 
 discuss issues and possibilities.
DTSTAMP:20260531T103409Z
LOCATION:Building D/room 2\, Workshops and AI Security Village
SUMMARY:Security for AI: AIDR Bastion as open source LLM firewall / AI prom
 pts reverse proxy - Andrii Bezverkhyi
URL:https://pretalx.com/bsidesluxembourg-2026/talk/SDCESA/
END:VEVENT
END:VCALENDAR