Hacking & Securing AI Systems: Playing with Fire and Controlling the Flare of AI

AI is the ultimate accelerant for application development – fueling innovation at breakneck speed and making the impossible look easy. But here’s the catch: fire is a tool until it’s out of control. In this session, we’re not just talking about AI risks – we’re playing with fire and watching what happens, straight from the terminal. We’ll exploit vulnerabilities, uncover adversarial tricks, and walk through real-world case studies that show just how easy it is to take advantage of AI risks (and how attackers are already doing it). Expect technical code examples and a behind-the-scenes look at how attackers manipulate AI – from jailbreaking LLMs to creating AI-driven zero-days. More importantly, we’ll cover how to fight fire with fire by strengthening prompts, setting up guardrails, spotting rogue agents, and running AI-specific red team exercises. Learn how to adapt to ensure AI delivers on its promise of a brighter future – instead of its burning threat of unforeseen risks.