BEGIN:VCALENDAR
VERSION:2.0
PRODID:Data::ICal 0.24
BEGIN:VEVENT
DESCRIPTION:   'Title: Defense in Depth for AI: Launching the AISECA Framew
 ork\n   Tags: Middle Easterns & Africans in Cyber Security (MEACS) | Creat
 or\n   Talk/Panel\n   When: Friday\, Aug 7\, 16:00 - 16:59 PDT\n   Where: 
 LVCCW Level 1 Hall 4 1306 (Middle Easterns & Africans in Cyber\n   Securit
 y (MEACS) Community) - [1]Map\n\n   Description:\n\n   Every week brings a
  new agentic AI attack and a new point solution\n   that claims to stop it
 . None of them stop all of it\, because agents do\n   not have one attack 
 surface\, they have many\, spread across the skills\n   they load\, the to
 ols they call\, the data they touch\, and the humans\n   who approve them.
  This talk introduces the AISECA Tiered Control\n   Framework\, an open\, 
 community-built model for defending agentic\n   workflows the way we defen
 d everything else that matters: in depth\, in\n   layers\, with no single 
 control carrying the whole load. We walk the\n   framework end to end\, th
 en go deep on one control to show how it works\n   in practice\, what it c
 atches\, what it misses\, and how it composes with\n   the controls around
  it. You will leave with a shared vocabulary for\n   agentic risk and a pr
 actical way to find the gaps in your own stack.\n   Built in the open by p
 ractitioners\, free to adopt\, and yours to\n   extend.\n\n   Speakers:Amb
 er Bennoui\,Karol Piekarski\n\n   SpeakerBio:  Amber Bennoui\n   No BIO av
 ailable\n   SpeakerBio:  Karol Piekarski\, DevOps Engineer\n\n   Karol Pie
 karski is a Lead DevOps Engineer working across cloud\n   infrastructure\,
  zero-trust architecture\, and AI and agentic security\n   for systems tha
 t serve hundreds of millions of consumers. His research\n   focuses on the
  security of large language models and autonomous\n   agents\, with an emp
 hasis on practical red-teaming and defensive\n   tooling that teams can ac
 tually operationalize rather than shelve.\n\n   His empirical work on abli
 teration and agentic framing reframes where\n   alignment actually breaks 
 down in agent pipelines: agentic framing\n   alone can collapse a model's 
 baseline safety\, while abliteration\n   matters mostly for the hardest co
 ntent and is highly\n   architecture-dependent. In 2026 he co-presented "M
 ove Fast\, Stay\n   Secure: Enterprise AI Agent Security in Practice" at t
 he Databricks\n   Data + AI Summit\, and spoke at SCaLE 23x on open source
  red-teaming\n   for LLMs. He was one of only two external contributors to
  the\n   Databricks Agentic AI Security Framework (DASF v3.0).\n\n   Karol
  is the creator of Sundew.sh\, an open source\, MCP-native AI agent\n   ho
 neypot platform that uses behavioral fingerprinting and a persona\n   engi
 ne for anti-fingerprinting\, now adopted by external research teams\n   st
 udying agent behavior in the wild. He was selected as a Wiz MVP last\n   y
 ear and this year received Wiz's Thought Leader award\, and he is\n   acti
 ve in the AISECA Working Group\, where he co-owns agentic security\n   ris
 k definitions.\n\n   He holds the CCSP\, CKA\, four AWS specialty certific
 ations along with\n   DataDog and Tines\, and he regularly judges and ment
 ors at hackathons\n   across Southern California.\n\n   '\n\n   1. #LVCCW_
 Level1_Hall4\n\n\n
DTEND:20260807T235900Z
DTSTART:20260807T230000Z
LOCATION:Middle Easterns & Africans in Cyber Security (MEACS) - LVCCW Level
  1 Hall 4 1306 (Middle Easterns & Africans in Cyber Security (MEACS) Commu
 nity)
SUMMARY:Defense in Depth for AI: Launching the AISECA Framework
END:VEVENT
END:VCALENDAR