Due to the proliferation and widespread use of deep neural networks (DNN), their Intellectual Property Rights (IPR) protection has become increasingly important. This paper presents a novel model watermarking method for an unsupervised image-to-image translation (I2IT) networks, named CycleGAN, which leverage the image translation visual quality and watermark embedding. In this method, a watermark decoder is trained initially. Then the decoder is frozen and used to extract the watermark bits when training the CycleGAN watermarking model. The CycleGAN watermarking (CycleGANWM) is trained with specific loss functions and optimized to get a good performance on both I2IT task and watermark embedding. For watermark verification, this work uses statistical significance test to identify the ownership of the model from the extract watermark bits. We evaluate the robustness of the model against image post-processing and improve it by fine-tuning the model with adding data augmentation on the output images before extracting the watermark bits. We also carry out surrogate model attack under black-box access of the model. The experimental results prove that the proposed method is effective and robust to some image post-processing, and it is able to resist surrogate model attack.
翻译:由于深神经网络(DNN)的扩散和广泛使用,它们的知识产权保护变得日益重要。本文件为未经监督的图像到图像翻译(I2IT)网络提供了一个新型的水标记模型,名为CypeGAN,它利用图像翻译的视觉质量和水印嵌入。在这种方法中,最初对水标记解码器进行了培训。然后,解码器被冻结,用于在培训CyopleGAN水标记模型时提取水标记位。CycleGAN水标记(CycleGANNAM)接受了特定损失功能的培训,并优化了在I2IT任务和水标记嵌入两个方面取得良好性能的功能。在水标记核查中,这项工作利用统计意义测试来确定模型的所有权。我们评估模型对图像后处理的稳健性,并通过对模型进行微调,在提取水标记部分之前添加数据加增量模型。我们还在黑箱访问模型和水标记嵌入水标记时进行了一些防御模型攻击。在模型访问后,试验结果是可靠的,测试结果,并证明是有效的抵抗模型。