BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//cfp.troopers.de//tr26-cfp//talk//G8FH3R
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-tr26-cfp-G8FH3R@cfp.troopers.de
DTSTART;TZID=CET:20260624T181500
DTEND;TZID=CET:20260624T184500
DESCRIPTION:As AI systems become part of critical products and workflows\, 
 they introduce a new security surface where attacks happen through languag
 e. In traditional security domains\, threat hunting focuses on signals suc
 h as network ports\, traffic patterns\, or system activity. In AI security
 \, the signals are different. Instead of packets and processes\, defenders
  analyze text interactions with models to identify malicious intent.\n\nEf
 fective threat hunting in AI systems requires more advanced tools. Signals
  hidden within natural language often require analyzing text using tools s
 uch as embedding models and perplexity to surface suspicious intent and an
 omalous behavior. In this talk we demonstrate a novel approach for conduct
 ing effective threat hunting in AI driven applications.
DTSTAMP:20260510T031057Z
LOCATION:Track 2
SUMMARY:From Packets to Intent: Hunting Adversaries in AI Telemetry - Raz T
 el-Vered
URL:https://cfp.troopers.de/tr26-cfp/talk/G8FH3R/
END:VEVENT
END:VCALENDAR