对抗制
增采样
计算机科学
利用
深度学习
人工智能
图像(数学)
领域(数学)
分割
图像分割
计算机安全
安全性分析
机器学习
数学
纯数学
作者
Zhaoxuan Wang,Shiyu Zhang,Yang Li,Quan Pan
摘要
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’ 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.
科研通智能强力驱动
Strongly Powered by AbleSci AI