BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//conference.wireshark.org//sf26eu//speaker//GQJXMJ
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-sf26eu-R9PZDM@conference.wireshark.org
DTSTART;TZID=CET:20261104T133000
DTEND;TZID=CET:20261104T143000
DESCRIPTION:At SharkFest '24\, we introduced the fundamentals of open-sourc
 e deep packet inspection (DPI) using nDPI. Since then\, network adversarie
 s and stealth VPN providers have significantly evolved\, rendering traditi
 onal methods like JA4 insufficient against heavily obfuscated traffic. Thi
 s 1-hour follow-up session is split into two core sections.First\, we expl
 ore advanced traffic fingerprinting techniques that surpass current state-
 of-the-art standards.\n\n- We will demonstrate how to leverage Wireshark t
 o capture\, dissect\, and label complex traffic streams to drive these new
  nDPI capabilities.\n- We address what happens when fingerprinting fails a
 gainst highly evasive protocols.\n- We will show how Wireshark data feeds 
 into a data pipeline to train Transformer-based AI models to unmask stealt
 h VPN traffic.\n- The session concludes with a live demonstration showcasi
 ng both advanced DPI extensions and the AI model detecting disguised traff
 ic in real time.
DTSTAMP:20260624T110251Z
LOCATION:Room 1
SUMMARY:Transformers in the Wire: Advanced DPI Fingerprinting and AI for St
 ealth VPN Detection - Luca Deri\, Daniele Sartiano
URL:https://conference.wireshark.org/sf26eu/talk/R9PZDM/
END:VEVENT
END:VCALENDAR