面向鲁棒三维医学图像分割的频域对抗训练
Frequency Domain Adversarial Training for Robust Volumetric Medical Segmentation
AI总结：
针对三维医学图像分割模型易受对抗攻击的问题，提出3D频域对抗攻击及带频率一致性损失的频域对抗训练方法，提升模型在干净和对抗样本上的性能权衡。
摘要：
在医疗健康等关键应用场景中，确保深度学习模型的鲁棒性至关重要。尽管近期深度学习进展提升了三维医学图像分割模型的性能，但这类模型易受对抗攻击，无法直接部署于实际应用。我们提出了一种针对三维医学图像分割模型的3D频域对抗攻击方法，证明了其相比传统输入域或体素域攻击的优势。基于所提攻击方法，我们提出了一种新颖的频域对抗训练方法，用于优化模型以抵御体素域和频域攻击。此外，我们提出了频率一致性损失来约束频域对抗训练，使模型在干净样本和对抗样本上的性能实现了更优的权衡。代码已公开于https://github.com/asif-hanif/vafa。
英文摘要：
It is imperative to ensure the robustness of deep learning models in critical applications such as, healthcare. While recent advances in deep learning have improved the performance of volumetric medical image segmentation models, these models cannot be deployed for real-world applications immediately due to their vulnerability to adversarial attacks. We present a 3D frequency domain adversarial attack for volumetric medical image segmentation models and demonstrate its advantages over conventional input or voxel domain attacks. Using our proposed attack, we introduce a novel frequency domain adversarial training approach for optimizing a robust model against voxel and frequency domain attacks. Moreover, we propose frequency consistency loss to regulate our frequency domain adversarial training that achieves a better tradeoff between model's performance on clean and adversarial samples. Code is publicly available at https://github.com/asif-hanif/vafa.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
