BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//open-source-conference-luxembourg-2026//sp
 eaker//WDHNWL
BEGIN:VTIMEZONE
TZID:Europe/Luxembourg
BEGIN:DAYLIGHT
DTSTART:20251007T000000
TZNAME:CEST
TZOFFSETFROM:+0200
TZOFFSETTO:+0200
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20251026T030000
RDATE:20261025T030000
TZNAME:CET
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20260329T030000
RDATE:20270328T030000
TZNAME:CEST
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
SUMMARY:AI Powered OSINT - Taranis AI - Peter Leitmann
DTSTART;TZID=Europe/Luxembourg:20261007T173000
DTEND;TZID=Europe/Luxembourg:20261007T180000
DTSTAMP:20260916T160801Z
UID:pretalx-open-source-conference-luxembourg-2026-QDRYDA@pretalx.com
DESCRIPTION:Taranis AI is an open-source OSINT platform built around the w
 orkflows of Cyber Threat Intelligence (CTI) analysts. It uses AI to suppor
 t information gathering and situational analysis\, while keeping the analy
 st at the centre of the process.\n\nThreat intelligence becomes much more 
 useful when it can be shared. Taranis AI can not only share intelligence p
 roducts\, but also connect independent instances and exchange intelligence
  through MISP\, allowing different organisations to collaborate while stil
 l maintaining their own environments and data.\n\nThis comes with some int
 eresting challenges. How do we integrate AI and Large Language Models whil
 e preserving human judgement and accountability? How do we share informati
 on between independent systems while keeping control over the data? And ho
 w much control should we hand over to AI in the first place? In this talk
 \, we will share our experience developing Taranis AI\, the decisions we h
 ave made so far\, what currently works\, and some of the problems we are s
 till working on.
LOCATION:CyberSecurity
URL:https://pretalx.com/open-source-conference-luxembourg-2026/talk/QDRYDA
 /
END:VEVENT
END:VCALENDAR