Adversarial attack vulnerability of medical image analysis systems: Unexplored factors

作者：Gerda Bortsova, Cristina González-Gonzalo, Suzanne C. Wetstein, Florian Dubost, Ioannis Katramados, Laurens Hogeweg, Bart Liefers, Bram van Ginneken, Josien P. W. Pluim, Mitko Veta, Clara I. Sá‎nchez, Marleen de Bruijne · 发表于：Medical Image Analysis · 年份：2021 · DOI：10.1016/j.media.2021.102141 · 被引用次数：125 · 研究领域：Adversarial Robustness in Machine Learning、Bacillus and Francisella bacterial research、Autopsy Techniques and Outcomes

Adversarial attacks are considered a potentially serious security threat for machine learning systems. Medical image analysis (MedIA) systems have recently been argued to be vulnerable to adversarial attacks due to strong financial incentives and the associated technological infrastructure. In this paper, we study previously unexplored factors affecting adversarial attack vulnerability of deep learning MedIA systems in three medical domains: ophthalmology, radiology, and pathology. We focus on adversarial black-box settings, in which the attacker does not have full access to the target model and usually uses another model, commonly referred to as surrogate model, to craft adversarial examples that are then transferred to the target model. We consider this to be the most realistic scenario for MedIA systems. Firstly, we study the effect of weight initialization (pre-training on ImageNet or random initialization) on the transferability of adversarial attacks from the surrogate model to the target model, i.e., how effective attacks crafted using the surrogate model are on the target model. Secondly, we study the influence of differences in development (training and validation) data between target and surrogate models. We further study the interaction of weight initialization and data differences with differences in model architecture. All experiments were done with a perturbation degree tuned to ensure maximal transferability at minimal visual perceptibility of the attacks. Our ...