Skip to content
Weaponized · 2 sources ·
Picture from the bankinfosecurity.com article
Image: bankinfosecurity.com

Robots Hacking Robots: AI Can Now Do Most of an OT Attack, Pending a Human Nod

Ourtake

The lab models had to ask permission before moving a robotic arm. Booz Allen's researchers say the models are learning faster than the guardrails.

What happened

Booz Allen Hamilton and Frenos separately tested frontier and open-weight AI models against an air-gapped OT lab network. Booz Allen reported that both frontier models succeeded across all eight attack scenarios, with human approval required before any kinetic action. The researchers said the attacks were often inefficient and noisy, and that some human guidance remained necessary.

Sources

Report a mistake