Architecting Trustworthy AI: From Design Principles to Live Defense

Are your AI applications secure by design, or are you patching vulnerabilities after deployment? With the rise of Agentic AI, autonomous actions, and shadow models, relying on traditional security boundaries is no longer an option. Join us to move beyond theory and see how a Secure AI by Design approach works in real environments. Learn how to govern external tools, secure models, and protect autonomous agents. We will explore how to implement proactive risk exposure via automated AI Red Teaming, secure the supply chain with model security, and defend against runtime threats like prompt injections across your entire AI infrastructure.