BEGIN:VCALENDAR
VERSION:2.0
PRODID:Data::ICal 0.24
BEGIN:VEVENT
DESCRIPTION:   'Title: Once Upon a Prompt: Fairy Tales That Explain AI Secu
 rity\n   Tags: Middle Easterns & Africans in Cyber Security (MEACS) | Crea
 tor\n   Talk/Panel\n   When: Friday\, Aug 7\, 12:00 - 12:59 PDT\n   Where:
  LVCCW Level 1 Hall 4 1306 (Middle Easterns & Africans in Cyber\n   Securi
 ty (MEACS) Community) - [1]Map\n\n   Description:\n\n   Prompt injection i
 s one of the biggest security challenges in AI\, but\n   it can be difficu
 lt to explain without diving into complex technical\n   details. This sess
 ion uses familiar fairy tales to make modern AI\n   attacks easy to unders
 tand and hard to forget. We’ll begin by\n   exploring the architectural 
 problem that makes prompt injection\n   possible and why LLMs can’t sepa
 rate instructions from data the way\n   traditional software can. From the
 re\, we’ll examine three real-world\n   AI security incidents\, each pai
 red with a classic story: Little Red\n   Riding Hood illustrates prompt in
 jection through trusted messengers\,\n   The Wolf in Sheep’s Clothing ex
 plains indirect prompt injection\n   hidden in untrusted content\, and The
  Trojan Horse demonstrates how\n   hidden instructions can lead to data ex
 filtration and agent\n   compromise. We’ll close by mapping practical de
 fenses to OWASP and\n   NIST guidance so attendees leave with clear mental
  models and\n   actionable techniques for building more secure AI applicat
 ions.\n\n   SpeakerBio:  Sana Talwar\n   No BIO available\n   '\n\n   1. #
 LVCCW_Level1_Hall4\n\n\n
DTEND:20260807T195900Z
DTSTART:20260807T190000Z
LOCATION:Middle Easterns & Africans in Cyber Security (MEACS) - LVCCW Level
  1 Hall 4 1306 (Middle Easterns & Africans in Cyber Security (MEACS) Commu
 nity)
SUMMARY:Once Upon a Prompt: Fairy Tales That Explain AI Security
END:VEVENT
END:VCALENDAR