BEGIN:VCALENDAR
VERSION:2.0
PRODID:Data::ICal 0.24
BEGIN:VEVENT
DESCRIPTION:   'Title: Zero-Cloud Threat Modeling: Vector Embedding Archite
 ctures for\n   Automated Vulnerability Detection\n   Tags: AI | DEF CON De
 mo Labs | Intermediate | AppSec | Threat\n   Intel/Hunting | DEF CON Demo 
 Labs\n   When: Friday\, Aug 7\, 13:00 - 13:45 PDT\n   Where: LVCCW Level 1
  Hall 3 900 (Demo Labs Track 4) - [1]Map\n\n   Description:\n\n   Traditio
 nal threat modeling is a tedious\, manual process prone to\n   human error
 . Conversely\, modern "AI" threat modeling tools almost\n   universally de
 pend on sending sensitive\, proprietary system\n   architectures to third-
 party APIs in cleartext.\n\n   We present AI Threat Modeler (AITM)\, a ful
 ly open-source\, zero-cloud\n   application designed to automate architect
 ure-driven STRIDE threat\n   modeling completely offline. AITM fundamental
 ly shifts how we analyze\n   system designs by replacing brittle\, keyword
 -based regex rules with a\n   local Semantic AI Engine.\n\n   Under the ho
 od\, AITM leverages sentence-transformers and an in-memory\n   FAISS vecto
 r database to embed a comprehensive\, 116+ component\n   knowledge base. D
 uring analysis\, a custom NetworkX graph builder\n   parses natural langua
 ge or structured architecture descriptions (via\n   spaCy) to map undocume
 nted architectural features to known CVE classes\n   and STRIDE categories
 .\n\n   Furthermore\, AITM introduces "Architecture Intelligence" using gr
 aph\n   traversal algorithms to automatically infer missing trust boundari
 es\n   and identify multi-step attack chains that standalone component\n  
  scanning misses. In this demo\, we will: Walk through the automated\n   i
 ngestion of a microservice architecture. Demonstrate how the local\n   FAI
 SS engine discovers semantic threats that evade keyword matching.\n   Show
  dynamic attack cha\n\n   SpeakerBio:  Ankit Vashisth\n\n   Ankit Vashisth
  is a Security Engineer with over 4 years of experience\n   in application
  security\, cloud security\, and DevSecOps. He has worked\n   on security 
 assessments across web\, mobile\, network\, and enterprise\n   systems for
  global clients. His interests include AI-driven security\n   tooling\, th
 reat modeling\, and security automation. Ankit actively\n   researches way
 s to apply AI to improve security architecture analysis\n   and vulnerabil
 ity detection.\n\n   Links:\n       GitHub - [2]https://github.com/ankitsp
 idy007/ai-threat-modeler\n   '\n\n   1. #LVCCW_Level1_Hall3\n   2. https:/
 /github.com/ankitspidy007/ai-threat-modeler\n\n\n
DTEND:20260807T204500Z
DTSTART:20260807T200000Z
LOCATION:Demo Labs - LVCCW Level 1 Hall 3 900 (Demo Labs Track 4)
SUMMARY:Zero-Cloud Threat Modeling: Vector Embedding Architectures for Auto
 mated Vulnerability Detection
END:VEVENT
END:VCALENDAR