BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//bsidesluxembourg-2026//talk//D3T9SA
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-D3T9SA@pretalx.com
DTSTART;TZID=CET:20260507T162000
DTEND;TZID=CET:20260507T170000
DESCRIPTION:Every LLM has flaws. It’s been proven that the guardrails on 
 every LLM can be bypassed. When you’re thinking about which ones to buil
 d your applications on\, what are the key risks you need to be aware of?\n
 In this talk\, we will dive into our testing methodology for scanning the 
 most popular LLMs for vulnerabilities where we generated hundreds of thous
 ands of prompts across categories including prompt injection\, malware\, o
 ffensive language\, and much more.\n\nWe’ll share our LLM risk matrix\, 
 and explain the best practices around minimizing the risk of hallucination
 s\, malicious content\, indirect prompt injection\, and more as you build 
 your LLM-powered applications.
DTSTAMP:20260412T024944Z
LOCATION:IFEN room 2\, Workshops and AI Security Village  (Building D)
SUMMARY:Making a risk-informed LLM choice - Jeremy Snyder
URL:https://pretalx.com/bsidesluxembourg-2026/talk/D3T9SA/
END:VEVENT
END:VCALENDAR