Mark Vaitsman
Manager of AI Security Research
Varonis
Webinar
+1 CPE
AI Under Attack: Lessons from 4 One-Click AI Exploits
One click. That’s all it took to turn AI assistants against their users and expose sensitive data.
Reprompt, RovoBlast, SearchLeak, and CoSnitch have been patched. But the pattern behind them remains: Enter. Evade. Escape.
Learn the blueprint behind these exploits and how to spot and stop the next one, no matter which AI tool it targets.
In this session, you’ll:
- See how Reprompt, RovoBlast, SearchLeak, and Cosnitch turned AI assistants into insiders with a single click
- Understand why built-in guardrails, and even cutting an assistant off from the internet, weren’t enough to stop data from leaving
- Learn how to apply the Enter, Evade, Escape framework to the AI tools your organization adopts
- See how Varonis secures the browser, the agent, and the data itself, so you can stop the next one-click exploit before your data walks out the door
Registration closed.
Registration has closed at this time. If you’d like to watch on-demand, click the link below.
Thank you for registering.
You’ll receive a confirmation email from Zoom shortly. Contact us if you do not receive it within 24 hours.
