In today’s AI-driven world, traditional cybersecurity isn’t enough. Generative AI systems can be exploited in new and unexpected ways—and that’s where AI Red Teaming comes in. Think of it as offensive security for your models, probing them before real attackers do.

In this hands-on session, we’ll unpack how red teaming works for GenAI: from simulating real-world attacks and prompt injection to uncovering hidden, risky capabilities. You’ll learn practical methodologies adversarial simulation, targeted testing, and capability evaluation, as well as how to operationalize them at scale.

We’ll also explore frameworks like the MITRE ATLAS Matrix, compliance alignment with NIST AI RMF and the EU AI Act, and must-know tools like Garak, PyRIT, and ART.

By the end, you’ll walk away with a practical playbook to proactively harden your AI systems, detect emerging threats, and build secure, responsible GenAI applications before adversaries get there first.