LLMs are being shipped to production faster than teams can secure them. In this talk, we’ll walk through the OWASP Top 10 LLM risks — not as a dry checklist, but through the real-world incidents that put them on the list. Then we’ll go further: watch a deliberately vulnerable AI app get attacked live on stage, see exactly how each exploit works, and then watch it get fixed. You’ll leave with a clear mental model of where LLM apps break, why they break, and what good actually looks like.
Supported by
