Location
Singapore and other locations to be announced soon.
Application deadline
Check back again when applications are open

Frontier AI Security Training (FAST)

Training the practitioners who secure frontier AI systems and the policymakers who govern them

Applications open soon

3-5 days
Intensive format for busy professionals
Two Cohorts
Technical & Governance Tracks
20 participants
in each cohort

Details

What is FAST?

Two cohorts.
One mission.

Frontier AI capabilities are advancing faster than the institutions responsible for governing them. The people who will determine how frontier AI security risks are governed and defended are making consequential decisions from an inadequate base. The research exists. The threat models, governance frameworks, and defensive techniques are documented. What's missing is the mechanism that moves these works to the people best positioned to act on them.

FAST builds the technical depth and governance fluency that frontier AI demands — through dedicated programs for security practitioners and for the policymakers who shape the rules around them. The first Singapore technical cohort ran April 20–26, 2026, as part of AI Security Bootcamp (AISB).

The next cohort planned for September/October 2026 in Singapore. Both technical and governance cohorts are fully-funded for selected participants.

Technical Track

FAST Technical Track is a 5 days intensive program for security professionals focused on securing frontier AI systems from emerging threats.

The intensive technical training is grounded in hands-on red/blue exercises that go deep on a smaller set of high-leverage skills and alignment on threat models and priorities. Participants leave with applied skills and peer relationships across the frontier AI security community.

A key impact outcome from the April cohort has been how the training turbocharges career transitions by facilitating the entry of high-potential talent into AI security and safety fields. Out of the cohort of 16 senior practitioners, 7 are transitioning to new AI security roles, 3 are launching independent research or ventures and 1 is spearheading an internal organizational pivot.

Governance Track (Policymakers)

A practical, three-day program tailored for senior leaders in cybersecurity policy. This intensive combines scenario-based learning with essential technical insights. Curriculum to be co-designed with government institutions and grounded in ongoing collaborative research on offensive cyber agents and agentic AI governance (Agent ID, verification mechanisms).


It caters specifically to those without a background in data science or machine learning, providing the necessary knowledge to participate effectively in technical discussions without requiring ML/data science expertise.

This is a first-of-kind program being built for October 2026 alongside Singapore International Cybersecurity Week (SICW).

Team

Portrait of David Williams-King

Lead Instructor

David Williams-King

ERA

Research Manager at ERA, upskilling fellows in technical AI safety research. PhD from Columbia in systems and security; previously CTO and cofounder of cybersecurity insurance startup Elpha Secure.

Portrait of Jannis Kirschner

Security Researcher

Jannis Kirschner

Jannis Kirschner is a Swiss Security Researcher and CTF player. With a passion for reverse engineering and exploit development, he loves to analyze cutting edge frontier technology, finding flaws in highly secured systems and complex applications. At Niantic he safeguards software used by millions of people on a daily basis by implementing security mitigations all over the software development lifecycle.

Portrait of Bary Levy

Curriculum

Bary Levy

AI Security Researcher

Independent researcher across ML and security, applying security mindset to AI alignment. Previously co-founder of an AI Security research startup, and found major vulnerabilities in ML stack including JupyterLab and vLLM.

Portrait of Nitzan Shulman

AI Security Advisor

Nitzan Shulman

Heron AI Security Initiative

Head of Cyber Security at Heron AI Security Initiative. 6+ years of security research specialising in IoT, robotics, malware, and AI security.

Interested in Frontier AI Security Training (FAST)?

Reach out to SASH to ask about applications, future cohorts, or related programs.