Red-team AI systems
Run and learn from practical exercises that expose how AI systems fail, where defenses help, and what responsible testing looks like.
AI Village
Public-interest AI security
AI Village brings hackers, researchers, engineers, and policymakers together through hands-on AI security education, red-team exercises, workshops, events, and open resources.
Recent event
Aug 6, 2026 · LVCC, Level 1, Room W603, Las Vegas, NV
AI Village returns to DEF CON 34 in LVCC W603 with competitions, DEF CON stage sessions, poster presentations, fireside chats, and demos.
View eventDEF CON Village
Generative Red Team
Hands-on workshops
Open resources
Community research
Public AI security education
What we do
AI Village connects education, experimentation, and community practice so people can understand, test, and secure AI systems.
Run and learn from practical exercises that expose how AI systems fail, where defenses help, and what responsible testing looks like.
Publish workshops, labs, and learning material for people moving from curiosity to hands-on AI security practice.
Bring hackers, builders, researchers, and policy-minded practitioners together at DEF CON and other community events.
Share technical writing, recaps, and open resources from the people doing the work.
Programs
Explore the major paths into AI Village: red teaming, workshops, events, and technical work.
A public red-team program focused on understanding and exercising real AI system failure modes.
Hands-on learning material for AI security, adversarial thinking, and practical experimentation.
Find upcoming events, DEF CON activity, schedules, recaps, and community challenges.
Technical writing, event recaps, and practical AI security observations.
Current activity
Recent events, posts, and resources from the AI Village community.
Recent event · Aug 6, 2026
AI Village returns to DEF CON 34 in LVCC W603 with competitions, DEF CON stage sessions, poster presentations, fireside chats, and demos.
LVCC, Level 1, Room W603, Las Vegas, NV
Connect with people learning, testing, building, and securing AI systems in public.