Black Hat USA

Location: DEF CON Telecom Village

This talk examines how exposed AI infrastructure is becoming a new adversary playground, as attackers and internet-scale scanners and bruteforcing target LLM gateways, MCP servers, local inference APIs, and AI developer tooling faster than defenders have built threat models for them.

Eli ran a purpose-built AI honeypot that simulated 16 LLM and AI infrastructure personas across 16 ports, returning framework-authentic responses, headers, errors, and protocol behaviors. In one 48 hour window, the system captured 3,993 requests from 327 unique source IPs, including 155 MCP probes and 344 AI API key probes. What emerged was not generic internet noise, but a repeatable playbook against the emerging AI stack: LiteLLM model-registration abuse, MCP resource enumeration, framework-aware credential brute forcing, and coordinated scanning for exposed local inference services.

Location: DEF CON Adversary Village

This is a 15 minute lightning talk with an intro/brief overview of the Cyber Threat Intelligence discipline. Topics covered include why it's so hard to identify and define what CTI is in the current industry, the different aspects of what can be expected from CTI, and the typical backgrounds of CTI practitioners.

Having been a part of CTI teams at organizations with a wide variety of resources and maturity levels, this talk provides a realistic, ground-level view of the industry and what your average CTI experience is like, not the curated experiences of Fortune 500 CTI teams we all see presenting on the main stage.

Location: DEF CON n00b Village