Benefiting from deep learning, defocus blur detection (DBD) has made prominent progress. Existing DBD methods generally study multiscale and multilevel features to improve performance. In this article, from a different perspective, we explore to generate confrontational images to attack DBD network. Based on the observation that defocus area and focus region in an image can provide mutual feature reference to help improve the quality of the confrontational image, we propose a novel mutual-referenced attack framework. Firstly, we design a divide-and-conquer perturbation image generation model, where the focus region attack image and defocus area attack image are generated respectively. Then, we integrate mutual-referenced feature transfer (MRFT) models to improve attack performance. Comprehensive experiments are provided to verify the effectiveness of our method. Moreover, related applications of our study are presented, e.g., sample augmentation to improve DBD and paired sample generation to boost defocus deblurring.

中文翻译：

---

通过相互引用的特征转移进行散焦模糊检测攻击。

受益于深度学习，散焦模糊检测（DBD）取得了显着进展。现有的 DBD 方法通常研究多尺度和多级特征以提高性能。在本文中，我们从不同的角度探索生成对抗图像来攻击 DBD 网络。基于图像中的散焦区域和聚焦区域可以提供相互特征参考以帮助提高对抗图像质量的观察，我们提出了一种新颖的相互参考攻击框架。首先，我们设计了一种分而治之的扰动图像生成模型，分别生成聚焦区域攻击图像和散焦区域攻击图像。然后，我们整合相互参考的特征转移（MRFT）模型来提高攻击性能。提供了全面的实验来验证我们的方法的有效性。此外，还介绍了我们研究的相关应用，例如，用于改进 DBD 的样本增强和用于促进散焦去模糊的配对样本生成。