Sara Gogic

AI is rapidly becoming an advisor, teacher, colleague, and decision-maker. But the more we trust it, the harder it becomes to notice when it is misleading us. Explore firsthand how AI trust is built, influenced and exploited. In this hands-on session you will put AI and your own judgment to the test. We will explore how AI earns our trust, how that trust can be manipulated and why confidence is not the same as truth. Expect to experiment, attack and question "secure AI" to gain understanding of what "trustworthy AI" really means. Leave with practical ideas for making AI safer in your products, your organization and your own everyday decisions by gaining a deeper understanding of AI security risks and how resilient AI systems can be designed and operated. This is a fully guided, no-code interactive session open to all backgrounds; no prior technical or security experience is required. Come ready to question the machine, challenge your assumptions and discover strategic ways to keep human judgment at the center of an AI-driven world.