Can I read FIBA: Frequency-Injection based Backdoor Attack in Medical Image Analysis on EtoBox?

FIBA: Frequency-Injection based Backdoor Attack in Medical Image Analysis by Feng, Yu; Ma, Benteng; Zhang, Jing; Zhao, Shanshan; Xia, Yong; Tao, Dacheng is a scholarly article available to read on EtoBox.

What is FIBA: Frequency-Injection based Backdoor Attack in Medical Image Analysis about?

In recent years, the security of AI systems has drawn increasing research attention, especially in the medical imaging realm. To develop a secure medical image analysis (MIA) system, it is a must to study possible backdoor attacks (BAs), which can embed hidden malicious behaviors into the system. However, designing a unified BA method that can be applied to various MIA systems is challenging due to the diversity of imaging modalities (e.g., X-Ray, CT, and MRI) and analysis tasks (e.g., classification, detection, and segmentation). Most existing BA methods are designed to attack natural image classification models, which apply spatial triggers to training images and inevitably corrupt the semantics of poisoned pixels, leading to the failures of attacking dense prediction models. To address this issue, we propose a novel Frequency-Injection based Backdoor Attack method (FIBA) that is capable of delivering attacks in various MIA tasks. Specifically, FIBA leverages a trigger function in the frequency domain that can inject the low-frequency information of a trigger image into the poisoned image by linearly combining the spectral amplitude of both images. Since it preserves the semantic

Author

Feng, Yu; Ma, Benteng; Zhang, Jing; Zhao, Shanshan; Xia, Yong; Tao, Dacheng

Published

2021

Language

EN