@inproceedings{07ed217b164945ae9a677e78bd2ec71b,
title = "DBA: Downsampling-Based Adversarial Attack in Medical Image Analysis",
abstract = "The next-generation of artificial intelligence technology has contributed significantly to the development of medical intelligence. However, the widespread use of deep neural networks (DNNs) has also brought about serious security threats. In this paper, we present an adversarial attack approach for deep learning-based image segmentation models in the field of medical image analysis. In our solutions, we propose a novel adversarial attack method, which is designed to exploit the DNNs{\textquoteright} generic down-sampling operation to ensure the effectiveness, stealthiness, and transferability of the attack. We perform the attack on two State-Of-The-Art (SOTA) models, DDANet and CaraNet in a general medical image dataset Kvasir-SEG, and a comprehensive evaluation shows that our attack is effective stealthy, and transferrable.",
keywords = "Adversarial Attack, Deep Neural Networks, Medical Image Segmentation",
author = "Zhaoxuan Wang and Shiyu Zhang and Yang Li and Quan Pan",
note = "Publisher Copyright: {\textcopyright} 2023 SPIE.; 3rd International Conference on Computer Vision and Pattern Analysis, ICCPA 2023 ; Conference date: 07-04-2023 Through 09-04-2023",
year = "2023",
doi = "10.1117/12.2684368",
language = "英语",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",
editor = "Linlin Shen and Guoqiang Zhong",
booktitle = "Third International Conference on Computer Vision and Pattern Analysis, ICCPA 2023",
}