BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//RecertHero//RecertHero CE//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
UID:96061424-4899-4b90-af50-a31a4eb4e427@recerthero.com
DTSTAMP:20260520T235512Z
DTSTART:20251224T081809Z
DTEND:20251224T091809Z
SUMMARY:Darwinian Offense: Generative Curricula for Autonomous Red Teaming-
  a Security Congress Encore
DESCRIPTION:AI has historically struggled to assist in offensive security d
 ue to a critical shortage of real-world training data. This session takes 
 a deep dive into the methodology behind recently published research design
 ed to overcome this limitation through adversarial self-learning. Followin
 g up on her popular Security Congress 2025 keynote\, researcher Alissa Kni
 ght will dissect a novel architecture where an AI teaches itself to hack n
 ot by studying past attacks\, but by engaging in a continuous\, high-stake
 s war game against itself. Attendees will learn the mechanics of this "sur
 vival of the fittest" loop\, where two competing agents—one constructing d
 efensive puzzles and the other evolving breaking strategies—force the emer
 gence of increasingly sophisticated API attacks without human intervention
 . The session will move from research theory to validation with a live dem
 onstration against a banking API using Ares\, a prototype implementation o
 f this autonomous framework.
URL:https://www.isc2.org/professional-development/webinars/security-briefing?commid=658693
LOCATION:Online (BrightTALK)
END:VEVENT
END:VCALENDAR