Rogue AI Agents (OWASP+Hands on security workshop)
Registration with the organizer
Complete your actual registration on the organizer's website.
Found by Moments · AI Safety Awareness Group Boston
Is this your event?About the event
I'm thrilled to run another hands-on Rogue Agents workshop, in person at the Boston Public Library!
This session is geared toward a technical audience interested in applied Agentic AI security.
What you'll get:
• A walkthrough of OWASP’s Top 10 for Agentic Applications and how impacts can manifest • A crash course in agent environments, how to test their behavior safely, and why/where higher risks can occur • A direct look at agent "trajectories" using Python tools (Petri, Inspect, and Google Colab)
Bring a laptop and expect to follow along step-by-step: less theory, more implementation. Prior experience with python or other programming languages, security, or LLM tools is helpful, but not required (as long as you’re comfortable learning by doing!). All levels are welcome and encouraged to pair with someone at a different stage of learning.
To follow along step-by-step in Google Colab (less theory, more practice), please bring a laptop and set up an API key from an AI provider ahead of time (OpenRouter/Anthropic/OpenAI).
When you arrive, ask for the study room or come directly to Mezzanine Study Room 2
The Library does not permit any outside food or beverage within the Study Rooms, and we abide by the Boston Public Library Code of Conduct. https://www.bpl.org/about-the-bpl/official-policies/appropriate-library-use/
