BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//talks.toorcon.net//toorcamp-2026//talk//CQDHLQ
BEGIN:VTIMEZONE
TZID:PST
BEGIN:STANDARD
DTSTART:20001029T030000
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10;UNTIL=20061029T100000Z
TZNAME:PST
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
END:STANDARD
BEGIN:STANDARD
DTSTART:20071104T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:PST
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20000402T030000
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=4;UNTIL=20060402T110000Z
TZNAME:PDT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
END:DAYLIGHT
BEGIN:DAYLIGHT
DTSTART:20070311T030000
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:PDT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-toorcamp-2026-CQDHLQ@talks.toorcon.net
DTSTART;TZID=PST:20260627T130000
DTEND;TZID=PST:20260627T135000
DESCRIPTION:The last two years represent a paradigm shift from AI as a "cha
 t assistant" to an autonomous agentic workforce. Meanwhile\, "vibe hacking
 " and prompt injection are rapidly evolving into machine-speed warfare dri
 ven by autonomous AI agents. As models continue their exponential paramete
 r growth\, threat actors are now leveraging agentic connectors for zero-cl
 ick data exfiltration (AgentFlayer) and utilizing AI-orchestrated espionag
 e campaigns (GTG-1002) that operate at speeds physically impossible for hu
 man defenders to counter. Furthermore\, "semantic corruption" through disi
 nformation networks\, like Pravda\, now target the models' internal logic 
 by flooding and poisoning their training and retrieval data.\n\nThis evolu
 tion is driven by persistent orchestration frameworks like GasTown and Ral
 phWiggum\, which move away from ephemeral sessions toward Git-backed work 
 ledgers and the "GUPP" (Execute Immediately) principle. While these system
 s offer massive productivity gains\, "vibe coding" builds software with in
 tent rather than manual review. We have fundamentally expanded the attack 
 surface while we have little visibility into the silent\, machine-to-machi
 ne\, exploitation of the "agent stack." This talk explores how these auton
 omous architectures have decoupled technical execution from human oversigh
 t\, requiring a complete rethink of enterprise trust boundaries. [183]
DTSTAMP:20260626T012116Z
LOCATION:Prime Dome
SUMMARY:Architectures of Autonomy: Adversarial Orchestration and the Collap
 se of "Human-in-the-Loop" Security - infosecanon
URL:https://talks.toorcon.net/toorcamp-2026/talk/CQDHLQ/
END:VEVENT
END:VCALENDAR