BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.coscup.org//coscup-2026//speaker//8BAALZ
BEGIN:VTIMEZONE
TZID:CST
BEGIN:STANDARD
DTSTART:20000101T000000
RRULE:FREQ=YEARLY;BYMONTH=1
TZNAME:CST
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-coscup-2026-AKWMBV@pretalx.coscup.org
DTSTART;TZID=CST:20260808T150000
DTEND;TZID=CST:20260808T154000
DESCRIPTION:This talk lays bare six months of intensive research\, centered
  on OpenClaw. By benchmarking against industry counterparts like NVIDIA’
 s NeMo-Guardrails and Hermes-Agent\, we provide insights that generalize a
 cross the entire personal AI assistant landscape.\n\nWe will conduct live 
 demonstrations of five real-world attack vectors: Sandbox Backend Hijack\,
  Subagent-to-Parent Injection\, Group Chat History Pollution\, Reply-chain
  Manipulation\, and Supply Chain Attacks. Following the exploits\, we’ll
  break down how to architect multi-layered defense-in-depth strategies. Fi
 nally\, we will propose a unified "SecurityResult" interface: a standardiz
 ed framework designed to let tools like NeMo Guardrails\, LLM Guard\, Pres
 idio\, Rebuff\, and OpenGuardrails plug in seamlessly. Our goal is to move
  Personal AI Assistant security away from "reinventing the wheel" and towa
 rd a unified industry standard.
DTSTAMP:20260713T132504Z
LOCATION:TR313
SUMMARY:Personal AI Assistant's Attack and Defense - scc
URL:https://pretalx.coscup.org/coscup-2026/talk/AKWMBV/
END:VEVENT
END:VCALENDAR