Date: 11/20/2025
Time: 12:00 pm - 1:00 pm
Description
AI is everywhere — and so are the privacy concerns that come with it. At its core, the most common forms of AI we use today are online digital services — and thus inherit the usual privacy risks of any internet-based tool. However, AI also introduces a set of unique and evolving risks. We’ll take a closer look at one of the newest developments in this area: indirect prompt injection — a technique that can trick AI tools into revealing or extracting private information. You’ll learn how this emerging form of AI manipulation works, why it matters, and how to protect yourself — as well as how similar techniques are being used in academic contexts to manipulate systems and even mislead researchers.
Register for this Zoom workshop.
