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 semantics of the poisoned image pixels, FIBA can perform attacks on both classification and dense prediction models. Experiments on three benchmarks in MIA (i.e., ISIC-2019 for skin lesion classification, KiTS-19 for kidney tumor segmentation, and EAD-2019 for endoscopic artifact detection), validate the effectiveness of FIBA and its superiority over state-of-the-art methods in attacking MIA models as well as bypassing backdoor defense. Source code will be available at https://github.com/HazardFY/FIBA.
翻译:近年来,AI系统的安全性引起了越来越多的研究关注,特别是在医学成像领域。为了开发一个安全的医学成像分析(MIA)系统,必须研究可能发生的后门攻击(BAs),这可能把隐藏的恶意行为嵌入系统中。然而,由于成像方式(如X-Ray、CT和MRI)和分析任务(如分类、检测和分解)的多样性,设计一个统一的BA方法具有挑战性。大多数现有的BA方法是为了攻击自然成像分类模型,这些模型应用空间触发器来训练图像,并不可避免地腐蚀中毒的像素的语义,从而导致攻击密集的预测模型。然而,为了解决这个问题,我们提议采用一个新的基于后门攻击方法(FIBA方法)来进行攻击。具体地说,FIBAA在频率域中利用一个触发功能,可以将低频级的触发图像输入到下方图像中,通过直线将ISISB/20的温度模型组合起来,将IBA的直径直径机路路路路路路路路路路路路路机作为FIA的图像的直路标,将ILIA-IBILIA的图像作为FA的Silal-ILA级标的Silvial-IL 。它在三个的图像的Silal-limamasl的Silalbs的图像的测算进行。在三个的测算上维持了。它可以保存了三个的测算。