#healthcare-ai-risks

[ follow ]
#ai-security-vulnerabilities #prompt-injection-attacks #medical-record-manipulation #patient-safety
Healthcare
fromTheregister
3 weeks ago

AI doctor's assistant swayed to change scrips - researchers

Healthcare AI systems can be manipulated through prompt injection techniques to bypass safety measures, reveal system instructions, and generate harmful recommendations that persist in patient records.
Healthcare
fromFuturism
3 weeks ago

ChatGPT Health Is Staggeringly Bad at Recognizing Life-Threatening Medical Emergencies

ChatGPT Health fails to identify medical emergencies in over half of cases, incorrectly advising patients to stay home instead of seeking immediate hospital care.
[ Load more ]