AI brief
An IEEE Spectrum article sponsored by VicOne discusses how physical AI changes robot safety, shifting from whether a machine stays safe when something goes wrong to whether it stays safe when an attacker alters what it sees, decides, or does.
Why it matters: It highlights that security against manipulation of a robot's perception and decisions is a growing safety concern as AI is embedded in physical machines.
Written by AI from IEEE Spectrum AI's published text.
Source
“This article is brought to you by VicOne . Robot safety has traditionally asked: Can a machine remain safe when something goes wrong?”
Reporting from a publisher outside the organisation being covered.
Read original story ↗