Everyone is building AI, but how do you secure it?

As AI systems shift from static models to autonomous, agentic workflows, the risks stop being theoretical and start showing up in production. Prompt injection, data leakage, misuse, and unintended behavior are no longer edge cases: they’re part of everyday reality. In a world racing to adopt AI, speed without security creates fragility. The real question is no longer if AI systems will be attacked or misused, but whether we’re ready to detect, understand, and respond when it happens.

Join us for an open, technical, and grounded discussion led by Chris Meidinger, a cybersecurity veteran with over 20 years of experience in infosec, cyber defense, and secure communications. Chris currently advises organizations across Europe at Palo Alto Networks, focusing on pragmatic detection-and-response strategies for securing AI systems in real-world environments.

Together, we’ll explore:

• How AI threats differ from traditional application security
• Why detection and response are essential for agentic workflows
• What “secure-by-design” realistically looks like for AI systems
• How teams can deploy AI responsibly, without freezing innovation

📍 Where: Lenovo HQ, Calea Floreasca 169A (vis-a-vis de Promenada Mall)
🕕 When: 21th of January, 18:30
Let’s rethink how we secure AI before scale turns risk into reality.