Secure and Robust Machine Learning for Healthcare: A Survey
It tackles the critical issue of securing ML systems in healthcare, which is essential for patient safety and data confidentiality, but it is incremental as it primarily reviews existing challenges and methods.
This survey addresses the problem of security and privacy vulnerabilities in machine learning and deep learning applications within healthcare, highlighting the need for robust methods to protect against adversarial attacks and ensure data privacy.
Recent years have witnessed widespread adoption of machine learning (ML)/deep learning (DL) techniques due to their superior performance for a variety of healthcare applications ranging from the prediction of cardiac arrest from one-dimensional heart signals to computer-aided diagnosis (CADx) using multi-dimensional medical images. Notwithstanding the impressive performance of ML/DL, there are still lingering doubts regarding the robustness of ML/DL in healthcare settings (which is traditionally considered quite challenging due to the myriad security and privacy issues involved), especially in light of recent results that have shown that ML/DL are vulnerable to adversarial attacks. In this paper, we present an overview of various application areas in healthcare that leverage such techniques from security and privacy point of view and present associated challenges. In addition, we present potential methods to ensure secure and privacy-preserving ML for healthcare applications. Finally, we provide insight into the current research challenges and promising directions for future research.