On-demand webinar

How to Trap an AI Attacker: BlackSea’s Prompt-Injection-Free Approach

An open-source active honeypot that turns an AI attacker's own reasoning against it. Dario Pasquini, co-creator of BlackSea, shows how it detects, profiles, and disrupts autonomous AI attacks — with no prompt injection.

  • Why autonomous AI attackers change the defender's playbook
  • How BlackSea works without any prompt injection
  • The reward-hacking idea behind its agentic phishing baits
  • Results across 10 autonomous pentest systems and 6 frontier models
  • What's next for the open-source project
Duration
40 min.
Format
On-demand
Built for
Security researchers, red teamers & AI security engineers
Access recording

Watch the on-demand recording and download the slide deck.

Watch Webinar
Featured speakers

Built by practitioners. Speaking to practitioners.

Dario Pasquini

Dario Pasquini

Head of AI at Cracken

Dario Pasquini, PhD, is Head of AI at Cracken and co-creator of BlackSea. He has spent a decade in adversarial machine learning — from early work manipulating generative models in 2019, through attacks on federated learning and password-guessing systems, to LLM security. He authored the Mantis honeypot research ("Aiming Back the AI Archer") and now leads Cracken's AI Lab.

As covered in the webinar

BlackSea traps the attacker. Cracken runs the offense.

BlackSea is the open-source deception layer from Cracken's AI Lab. The platform behind it runs the full offensive kill chain against your own infrastructure — continuously, and under your control. Book a demo to see it against your targets.