论文标题
用于压缩感应MRI的局部对抗伪影
Localized adversarial artifacts for compressed sensing MRI
论文作者
论文摘要
随着对图像重建任务的深度神经网络（DNN）的兴趣，它们的可靠性已受到质疑（Antun等，2020； Gottschling等，2020）。然而，最近的工作表明，与完全正则化的总变化（TV）最小化相比，DNNS以$ \ ell^2 $ - 重建误差的形式显示出与对抗噪声相似的鲁棒性（Genzel等人，2022年）。我们考虑使用$ \ ell^\ infty $ norm的鲁棒性概念，并认为本地化的重建伪像比$ \ ell^2 $ -Error更相关。我们创建对抗性的扰动，以实现不足的磁共振成像测量（在频域中），该测量在电视调节重建中诱导严重的局部伪影。值得注意的是，相同的攻击方法对基于DNN的重建不是有效。最后，我们表明，这种现象是可以保证精确恢复的重建方法所固有的，就像用$ \ ell^1 $或TV-最小化的压缩传感重建一样。
As interest in deep neural networks (DNNs) for image reconstruction tasks grows, their reliability has been called into question (Antun et al., 2020; Gottschling et al., 2020). However, recent work has shown that, compared to total variation (TV) minimization, when appropriately regularized, DNNs show similar robustness to adversarial noise in terms of $\ell^2$-reconstruction error (Genzel et al., 2022). We consider a different notion of robustness, using the $\ell^\infty$-norm, and argue that localized reconstruction artifacts are a more relevant defect than the $\ell^2$-error. We create adversarial perturbations to undersampled magnetic resonance imaging measurements (in the frequency domain) which induce severe localized artifacts in the TV-regularized reconstruction. Notably, the same attack method is not as effective against DNN based reconstruction. Finally, we show that this phenomenon is inherent to reconstruction methods for which exact recovery can be guaranteed, as with compressed sensing reconstructions with $\ell^1$- or TV-minimization.
