Medical AI and Radiologist Experts May Be Vulnerable to Adversarial Attacks
Artificial intelligence (AI) models that evaluate medical images have the potential to speed up and improve the accuracy of cancer diagnoses, but they may also be vulnerable to cyberattacks. In a new study, University of Pittsburgh researchers simulated an attack that falsified mammogram images, fooling both an AI breast cancer diagnosis model and human breast imaging radiologist experts.
The study, published today in Nature Communications, brings attention to a potential safety issue for medical AI known as "adversarial attacks," which seek to alter images or other inputs to make models arrive at incorrect conclusions.
AI-based image ...