Research
AI Takes Control of Robotic Arm in 16 Minutes Flat
First reported darkreading.com
Page published
Earliest dated coverage: 16 Oct 2026 · First observed: 16 Oct 2026 · Latest dated coverage: 16 Oct 2026
Coverage timeline
Single-source research — one report is available.
Why it matters
Booz Allen's tests demonstrate how AI-driven attacks can rapidly exploit OT misconfigurations and turn network access into physical device control.
Booz Allen's laboratory tests found that commercial AI models could identify misconfigured OT devices, traverse multiple network layers, and trigger physical actions. In one test, a model took control of and moved a robotic arm within 16 minutes; the report describes controlled testing rather than a real-world intrusion.