Robust convolutional neural networks against adversarial attacks on medical images

作者：

Highlights：

• We quantify the scale of adversarial perturbations imperceptible to clinicians.

• Noise might cause CNNs’ vulnerability to adversarial medical images.

• We propose sparsity denoising operators for boosting CNNs’ robustness.

摘要

•We quantify the scale of adversarial perturbations imperceptible to clinicians.•Noise might cause CNNs’ vulnerability to adversarial medical images.•We propose sparsity denoising operators for boosting CNNs’ robustness.

论文关键词：CNNs,Adversarial examples,Sparsity denoising

论文评审过程：Received 12 September 2021, Revised 29 June 2022, Accepted 21 July 2022, Available online 22 July 2022, Version of Record 27 July 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2022.108923