Robustification of Segmentation Models Against Adversarial Perturbations In Medical Imaging
This addresses the security of medical imaging segmentation models, which is crucial for healthcare applications, though it is incremental as it builds on existing defense concepts for classification models.
The paper tackles the problem of defending segmentation models against adversarial attacks in medical imaging by proposing a novel defense framework that operates without modifying the target models and is attack-agnostic, achieving better performance than existing methods as shown empirically.
This paper presents a novel yet efficient defense framework for segmentation models against adversarial attacks in medical imaging. In contrary to the defense methods against adversarial attacks for classification models which widely are investigated, such defense methods for segmentation models has been less explored. Our proposed method can be used for any deep learning models without revising the target deep learning models, as well as can be independent of adversarial attacks. Our framework consists of a frequency domain converter, a detector, and a reformer. The frequency domain converter helps the detector detects adversarial examples by using a frame domain of an image. The reformer helps target models to predict more precisely. We have experiments to empirically show that our proposed method has a better performance compared to the existing defense method.