Query-based black-box attack against medical image segmentation model

With the extensive deployment of deep learning, the research on adversarial example receives more concern than ever before. By modifying a small fraction of the original image, an adversary can lead a well-trained model to make a wrong prediction. However, existing works about adversarial attack and defense mainly focus on image classification but pay little attention to more practical tasks like segmentation. In this work, we propose a query-based black-box attack that could alter the classes of foreground pixels within a limited query budget. The proposed method improves the Adaptive Square Attack by employing a more accurate gradient estimation of loss and replacing the fixed variance of adaptive distribution with a learnable one. We also adopt a novel loss function proposed for attacking medical image segmentation models. Experiments on a widely-used dataset and wellknown models demonstrate the effectiveness and efficiency of the proposed method in attacking medical image segmentation models. The implementation code and extensive analysis are available at https://github.com/Ikracs/medical_attack. (C) 2022 Elsevier B.V. All rights reserved.

Automated summary

Adversarial attacks have gained more attention with the widespread use of deep learning, but existing research primarily focuses on image classification rather than more practical tasks like segmentation. This work introduces a query-based black-box attack that effectively targets medical image segmentation models.