When AI Becomes the Threat: Cybersecurity in the New Age of Agentic AI

AI just went from tool to weapon, and the Anthropic breach proves it.

Chinese state actors used a single jailbreak prompt to turn Claude Code into an autonomous hacking machine — scanning targets, generating exploits, and stealing data from 30 organizations. No hacking team needed. Just one operator and an AI agent running at machine speed.

What used to take a skilled hacker team of many, now takes one person with the right prompt. The threat landscape just fundamentally changed.

NVTC is bringing together three experts who live at the intersection of agentic AI and national security.

Your panel:

• Ken Huang, AI & Blockchain Expert
  Author of Securing AI Agents
  He will break down his MAESTRO framework, the defensive playbook that goes beyond basic jailbreak detection.
• Rob Joyce, Former NSA Cybersecurity Director
  He will address how nation-states are weaponizing commercial AI tools and what regulatory frameworks can stop them.
• Ian Webster, CEO, Promptfoo
  He will share a live demo: How attackers chain “innocent” prompts into full espionage workflows (and how to stop them).
• Moderated by: KJ Lian, AWS Global Civilian Government

You’ll walk away with:

• Technical defenses AI developers must build in now
• Policy frameworks that can actually deter state actors
• Red teaming strategies to stress-test your AI before attackers do
• How to use agentic AI defensively for threat hunting
• Real vs. hype: What’s an actual agentic threat vs. fancy automation

The bottom line: AI is now both the weapon and the shield. Come learn how to use it right.

Agenda

8:45 – 9:15 AM | Registration & Networking
9:15 – 11:00 AM | Program

Speakers

Sponsors

Register today:

1. Select the ticket to the right.
2. Click “Checkout”
3. Enter all relevant information in.
4. Pay for your ticket.

To register, members need to have an NVTC profile. If you are unable to register, email membership@nvtc.org.

Registration Policies