Abstract
Deep learning (DL) models are highly vulnerable to adversarial attacks for medical image classification. An adversary could modify the input data in imperceptible ways such that a model could be tricked to predict, say, an image that actually exhibits a malignant tumor to a prediction that it is benign. However, the adversarial robustness of DL models for medical images is not adequately studied. DL in medicine is inundated with models of various complexity—particularly, very large models. In this work, we investigate the role of model complexity in an adversarial setting.