​AI Security Unplugged: Agentic Models & Red Teaming

​Join us for our March gathering of AI Security Collective. This is a forum where we will trek through the world of GenAI, exploring how it impacts cybersecurity and vice-versa.

​Each month we will invite different speakers and solution providers to explore different aspects of this fast-moving domain.

​Schedule

• ​1800: Doors Open

• ​18:20: Kick Off Introduction

• ​18:30: AI with Agents by Spyros Gasteratos

• ​19:15: Gamifying AI Red Teaming by Sam Watts

• ​20:00: Networking

• ​21:00: Home Time

​AI with Agents: A statistically organized chaos primer

​Spyros is a seasoned security leader with nearly two decades of experience, from analyst to CISO. He is the the founder of Smithy.security and maintains the OWASP project OpenCRE.org. AI models with agent capabilities is THE unmistakable trend of 2025 judging by the socials. But what is this agent capability that linkedin influencers rave about? In this talk we will discuss what are AI agents. We will provide some examples of popular AI agents and provide examples of popular projects and products with agentic capabilities.

​Gamifying AI Red Teaming

​​Sam is a product manager at Lakera. He has spent the last decade building software and companies at the intersection of security and compliance with deep tech. AI security is crucial for current and future digital safety, preventing sensitive data leaks and system compromises. Without robust security mechanisms, confidential information and intellectual property are at risk. This session will share insights from the world’s largest AI red team and discuss what gamifying AI red teaming (Gandalf) can teach us about safeguarding AI systems.