A machine and human reader study on AI diagnosis model safety under attacks of adversarial images
Sign Up to like & getrecommendations! Published in 2021 at "Nature Communications"
DOI: 10.1038/s41467-021-27577-x
Abstract: While active efforts are advancing medical artificial intelligence (AI) model development and clinical translation, safety issues of the AI models emerge, but little research has been done. We perform a study to investigate the behaviors… read more here.
Keywords: model safety; model; diagnosis model; adversarial images ... See more keywords
Using Adversarial Images to Assess the Robustness of Deep Learning Models Trained on Diagnostic Images in Oncology
Sign Up to like & getrecommendations! Published in 2022 at "JCO Clinical Cancer Informatics"
DOI: 10.1200/cci.21.00170
Abstract: PURPOSE Deep learning (DL) models have rapidly become a popular and cost-effective tool for image classification within oncology. A major limitation of DL models is their vulnerability to adversarial images, manipulated input images designed to… read more here.
Keywords: robustness models; oncology; learning models; deep learning ... See more keywords