AI Village @ DEF CON 34

📅 Dates:
📍 Location: LVCC, Level 1, Room W603, Las Vegas, NV

AI Village returns to DEF CON 34 in LVCC W603 with competitions, Creator Stage talks, poster presentations, fireside chats, and demos.

AI Village at DEF CON 34 announcement with a retro computer and geckos: 12 Creator Stage talks, 20 poster presentations, 6 fireside chats, at LVCC Level 1, Room W603.

We’re back at DEF CON 34 with a packed program spanning offensive AI security, research, live demos, competitions, and community discussion.

2 competitions · 12 Creator Stage talks · 20 poster presentations · 6 fireside chats

Village hours: 10:00 AM–5:00 PM daily

Competitions

HalCTF: Hostile Autonomous Layer CTF is an agentic security competition where you never touch the targets; your agent does. Build an autonomous agent, package it as an OCI container, and deploy it against sandboxed challenges. All model inference runs through our centralized service, so nobody wins on GPU budget. Compete solo or in teams of up to five.

We’ll announce the second competition shortly.

Talks and Fireside Chats

Twelve talks on the Creator Stage across the weekend, plus six fireside chats. The full speaker lineup and session times will be published separately.

Poster session

Poster sessions are new at AI Village. We have academic DNA, and poster sessions are an essential part of conferences, but they are not talks. You walk up, ask a question, challenge an assumption, and join the discussion with the author. We’re bringing that to DEF CON with a hacker twist.

Our inaugural poster track focuses on adversarial attacks against agents and agentic systems, including threat models, evaluations, tooling, reproductions, negative results, and work in progress. Final poster files are being added to the archive as authors submit them.

Posters

A random assortment for this event.

6 of 18 posters

  • Agent-to-Agent Worm Propagation in MCP-Based AI Systems

    Utku Yildirim (Cobalt.io & Hoffmann Cybersecurity), Ozgun Kultekin (Trendyol Group)

  • Beyond CTFs: Engineering AI Agents for Real-World Web Pentesting

    Dhruva Goyal (BugBase), Sitaraman Subramanian (BugBase)

  • Block Means Yes: Extracting Protected Agent Data Through a Guard’s Own Refusal Signal

    Larry Suto

  • Confused Deputies in Slack: Exploiting Agentic AI in Production Environments

    Rodney Beede (Life360)

  • Detecting unauthorized tool calls using Ollama and Splunk

    Anshumaan Mishra (Independent Researcher)

  • Don't Block — Bifurcate

    Kastriot Fetahaj (Kosova Cyber Team), Robert Shala (DefCon Group Prishtina), Blerim Rexha (University of Prishtina)

View all posters for DEF CON 34

Get involved

If you are at hacker summer camp, come by, ask questions, try the demos, and join the discussion.