Skip to main content
aaronininfosec

Speaking

I speak about AI agent security and how security teams build in the AI era. Recent talks are below, with the full write-ups and slides where they exist.

Keynote
AI Agent Security

Securing Autonomous AI Agents

Opening keynote · SF AppSec & DevSecOps Summit · May 14, 2026 · San Francisco

You cannot prevent an agent from being manipulated, but you can make it not matter when it is. The control plane is the blast radius.

The talk lays out five blast-radius controls for autonomous agents. Each one has its own page with a code example:

  1. 01Capability scopingLeast privilege per invocation, not per agent.
  2. 02Sandboxed executionDefault-deny everything outside the sandbox.
  3. 03Human-in-the-loop gatingCurate irreversible actions. Gate them in code, not policy.
  4. 04Behavioral auditTrust syscalls, not narratives.
  5. 05Agent identityFirst-class principal. Not a shared service account.
Lightning talk
Panel

Challenge the AI Guys

Lightning talk and panel · RSA Conference 2026 · San Francisco

Security people need to be builders in the AI era, not just gatekeepers. A lightning talk followed by a live debate on the benefits and risks of AI in security.

Read the talk
Panel
AI Security

RBLN West 2026

Panelist · Nov 4, 2026 · San Francisco

Joined a panel of security leaders at RBLN West, a gathering focused on offensive and defensive security, systemic cyber resilience, and AI in operational settings.

Earlier

I have also spoken at BSidesSF and Hardly Strictly Security, and co-led the security villages and capture-the-flag competitions at BSidesSF from 2020 to 2023.