"These targets are some of the easiest things that I've broken in my entire career. That's a bit dangerous when you have this ease of exploitation connected to sensitive use cases."
"Researchers said they altered the bot's baseline knowledge by feeding it fake regulatory updates. They convinced the system that COVID-19 vaccines had been suspended and changed the standard OxyContin dose to 30 milligrams every 12 hours - triple the typical levels for most adults."
"We take security research seriously and welcome responsible disclosure. Our security and clinical safety programs include ongoing adversarial testing, and we appreciate researchers who help us do that."
Security researchers at Mindgard demonstrated critical vulnerabilities in Doctronic's AI-powered medication renewal system by manipulating it to triple OxyContin dosages, falsely classify methamphetamine as therapeutic, and spread misinformation about COVID-19 vaccines. The researchers altered the system's baseline knowledge by injecting fake regulatory updates. While Doctronic operates within Utah's regulatory sandbox for legitimate use, researchers warn that underlying system vulnerabilities could pose serious risks if safeguards fail. Doctronic acknowledged the security research and stated it welcomes responsible disclosure as part of ongoing adversarial testing programs.
#ai-security-vulnerabilities #healthcare-technology #red-teaming-testing #medication-safety #regulatory-compliance
Read at Axios
Unable to calculate read time
Collection
[
|
...
]