Adversarial Attack Vulnerability of Medical Image Analysis Systems: Unexplored Factors

Understand

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.