BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//hack-lu-2025//talk//U3ZG7S
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-hack-lu-2025-U3ZG7S@pretalx.com
DTSTART;TZID=CET:20251021T151500
DTEND;TZID=CET:20251021T154500
DESCRIPTION:[IntelMQ](https://intelmq.org) is a great tool for automating s
 tructured IT security data feeds for CERTs: need to process all of shadows
 erver for a country? IntelMQ can easily do it. Need to alert on all vulner
 able devices that shodan knows about? Sure! \n\nBut what about unstructure
 d text? Many reports (CTI reports) contain lots of relevant information (I
 oCs\, TTPs\, etc.)\, but often in prose or only in semi-structured formats
  (hidden in a table\, etc.).\nFor information extraction\, LLMs and other 
 AI models (BERT\, etc.) proved their merit already.\n\nThe presents will s
 how how they extended intelmq to support \nthese AI models and how the com
 bination lends itself (semi-) automating a CTI analyst.\n\nIntelMQ to MISP
  output included \;-)
DTSTAMP:20260217T125939Z
LOCATION:Europe
SUMMARY:intelmq.ai - adding ML model support to intelmq - Aaron Kaplan\, Se
 bastian Wagner\, Jürgen Brandl
URL:https://pretalx.com/hack-lu-2025/talk/U3ZG7S/
END:VEVENT
END:VCALENDAR