论文标题
混音器：使用图像混音的DNN水印
Mixer: DNN Watermarking using Image Mixup
论文作者
论文摘要
在部署之前保护DNN模型的知识产权至关重要。 DNN应执行两个主要任务：其主要任务和水印任务。本文提出了轻巧，可靠和安全的DNN水印，试图在这两个任务之间建立牢固的联系。使用训练或测试样品中的图像混音生成触发水印任务的样品。这意味着，有无限的触发因素不限于用于在训练中嵌入水印的样品。针对不同数据集的图像分类模型进行的广泛实验以及将它们暴露于各种攻击中，表明拟议的水印提供了具有足够水平的安全性和鲁棒性的保护。
It is crucial to protect the intellectual property rights of DNN models prior to their deployment. The DNN should perform two main tasks: its primary task and watermarking task. This paper proposes a lightweight, reliable, and secure DNN watermarking that attempts to establish strong ties between these two tasks. The samples triggering the watermarking task are generated using image Mixup either from training or testing samples. This means that there is an infinity of triggers not limited to the samples used to embed the watermark in the model at training. The extensive experiments on image classification models for different datasets as well as exposing them to a variety of attacks, show that the proposed watermarking provides protection with an adequate level of security and robustness.
