SecAppDev 2026 Faculty
Natalie Isak
ML Engineer, Microsoft
Natalie Isak is an AI safety engineer at Microsoft who focuses on building scalable, impactful AI systems. She graduated from Cornell University and brings experience across both research and product development. She holds multiple patents in AI safety and has published at leading peer-reviewed venues. Her current work centers on developing monitoring systems and mitigation strategies for emerging AI risks, with an emphasis on privacy-preserving and compliant approaches.
AI Memory, Mapped
Deep-dive lecture by Natalie Isak in room West Wing
Monday June 1st,
16:00 - 17:30
Also available as a recorded session on
Tuesday June 2nd,
11:00 - 12:30
AI memory is not just another RAG plugin; it is a stateful, persistent attack surface. Securing it requires new threat models, new detection primitives, and architectural decisions made well before deployment.
Key takeaway: Treat AI memory as an attack surface; design for safety and observability from day one.
Slides available for download
AI Memory, Mapped
Deep-dive lecture by Natalie Isak in room Heilige-Geesttafel
Tuesday June 2nd,
11:00 - 12:30
Also available as a recorded session on
Tuesday June 2nd,
11:00 - 12:30
AI memory is not just another RAG plugin; it is a stateful, persistent attack surface. Securing it requires new threat models, new detection primitives, and architectural decisions made well before deployment.
Slides available for download