AI Security Night
Details
Hey everyone,
We’re back with a new event in Amsterdam focused on building with AI in a secure and efficient way.
Don't forget to RSVP now
TALK #1 - Breaching LLM-Powered Applications - Overcoming Security and Privacy Challenges
This session explores the security and data privacy challenges of AI applications using LLMs, covering issues like prompt injection, key leakage, and data misuse. It highlights how general security flaws affect LLM behavior and provides strategies for compliance and best practices to build secure, LLM-powered applications.
Speaker : Brian Vermeer
Staff Developer Advocate for Snyk, Java Champion, and Software Engineer with over a decade of hands-on experience in creating and maintaining software. He is passionate about Java, (Pure) Functional Programming and Cybersecurity. Brian is a JUG leader for the Virtual JUG and the NLJUG. He also co-leads the DevSecCon community and is a community manager for Foojay. He is a regular international speaker on mostly Java-related conferences like JavaOne, Devnexus, Devoxx, Jfokus, JavaZone and many more. Besides all that, Brian is a military reserve for the Royal Netherlands Air Force and a Taekwondo Master / Teacher.
TALK #2 - Securing Multi-Tenant AI Platforms: Practical Lessons from OpenShift AI, GPUs, and MLOps
As more teams move from AI prototypes to shared enterprise platforms, security becomes a platform engineering problem: how do we let multiple teams train, experiment, and deploy models safely on the same infrastructure?
In this talk, I’ll share practical lessons from building multi-tenant AI/ML environments on Kubernetes and OpenShift AI, with a focus on GPU-backed workloads. We’ll cover workload isolation, access control, GPU partitioning, namespace and quota design, supply-chain considerations, observability, and governance patterns for regulated environments.
The session will stay engineering-oriented and vendor-neutral, with concrete examples of what can go wrong, what controls matter most, and how platform teams can enable AI adoption without compromising security.
Speaker : Luca Berton
Luca Berton is a cloud-native and AI platform architect based in Amsterdam. He works on enterprise Kubernetes, OpenShift AI, automation, MLOps, and secure infrastructure for large-scale and regulated environments. He is also the author of several technical books and courses on Kubernetes, Ansible, Linux, and AI/ML operations.
Agenda
- 6:00 pm: Venue opens - Join us for Drinks and Pizza!
- 6:30 pm: Talk 1
- 7:15 pm: Talk 2
- 20:30 pm: THE END
