JERUSALEM — Israeli researchers have developed a new artificial intelligence (AI) technique to protect medical devices from cyber threats, Ben Gurion University (BGU) in southern Israel said on Tuesday.
The new technique can protect medical devices from malicious operating instructions in a cyberattack, as well as human errors such as a technician’s configuration mistake or host PC software bugs.
It can protect complex medical devices such as CT (computed tomography), MRI (magnetic resonance imaging) and ultrasound machines, that are controlled by instructions sent from a host PC.
Abnormal or anomalous instructions introduce many potentially harmful threats to patients, such as radiation overexposure, manipulation of device components or functional manipulation of medical images.
The new technique uses AI that analyzes the instructions sent from the PC to the physical components using a new architecture for the detection of anomalous instructions.
This is a dual-layer architecture for the protection of the medical devices, focusing on the detecting two types of anomalous instructions.
The team successfully tested the new technique in a CT domain, using 8,277 recorded CT instructions.