Explore the Frontiers of AI and Cybersecurity
Join a selective group of cybersecurity professionals exploring the most impactful research areas in AI security - from secure model deployment to compute governance and alignment risks.
Over six weeks, you’ll deepen your understanding of critical AI safety topics, meet peers working at the intersection of AI and security, and connect directly with leading researchers from institutions like RAND, Irregular, and others in the Heron network.
Program Structure
Some Research We’re Interested In
​
​
​
​
​
​
​
What You’ll Gain
Cutting-edge knowledge
Understand current challenges and promising research directions in AI security
Community
Engage with select cybersecurity professionals interested in going deep on impactful work on security risks from advanced AI systems
Connections
Connect with a broader ecosystem of AI Security by engaging with practioners, researchers and field leaders
Next-step opportunities
Get inside access to career opportunities, startup ideas, skill building programs, mentorship and funding focused on reducing AI risks
Who This Is For
This seminar is designed for experienced cybersecurity professionals (typically 5+ years in the field) who want to:
-
Understand where their expertise can make the biggest impact on AI security

​
-
Transition into or expand their work in AI safety research
​
-
Contribute meaningfully to high-stakes discussions shaping the secure AI future
How to Apply
We’re curating a small, high-context group of 10-15 cybersecurity professionals to ensure valuable discussions and fit.
The process includes: