Gradient-based enhancement attacks in biomedical machine learning.

ABSTRACT: The prevalence of machine learning in biomedical research is rapidly growing, yet the trustworthiness of such research is often overlooked. While some previous works have investigated the ability of adversarial attacks to degrade model performance in medical imaging, the ability to falsely improve performance via recently-developed "enhancement attacks" may be a greater threat to biomedical machine learning. In the spirit of developing attacks to better understand trustworthiness, we developed two techniques to drastically enhance prediction performance of classifiers with minimal changes to features: 1) general enhancement of prediction performance, and 2) enhancement of a particular method over another. Our enhancement framework falsely improved classifiers' accuracy from 50% to almost 1

SUBMITTER: Rosenblatt M 

PROVIDER: S-EPMC9882585 | biostudies-literature | 2023 Aug

REPOSITORIES: biostudies-literature