Model Extraction Attacks on Privacy-Preserving Deep Learning Based Medical Services

Xinqian Wang, Xiaoning Liu, Xun Yi, Xuechao Yang, Iqbal Gondal

Abstract: Advancements in deep learning have enabled high-quality medical diagnostic services. Typically, high-tech corporations train deep learning models to provide these services to their clients. To access services, clients simply upload their medical data and receive predictions. However, due to the sensitivity of medical data, such services usually face privacy concerns from their clients. Additionally, service providers cannot directly deploy their models on clients’ devices, as the trained models are considered valuable intellectual property.