Beyond Scripted Attacks: AI Red-Team Agents Driven by Live C2 Feedback

​Most AI offensive-security agents can plan attacks and write payloads, but they rely on predefined tools and isolated attack stages.

What if an agent could watch the target and adapt as it goes?

During this webinar, Vladyslav Poddubnyi, founding cybersecurity researcher at Cracken, will share research on an autonomous red-team agent that uses live C2 telemetry to generate and adjust its actions in real time.

After initial execution, it moves into post-exploitation on its own, adapting to the host's configuration, privileges, available tools, and defenses based on what it observes.

You'll learn:

• ​How live C2 feedback makes AI red teaming more adaptive

• ​The results against updated Windows 11

• ​The open challenges in reliability, safety, and operator control.

​Who should attend:

Red teamers, security researchers, threat detection engineers, cybersecurity engineers, offensive security engineers, penetration testers