Recently, the research on protecting the intellectual properties (IP) of deep neural networks (DNN) has attracted serious concerns. A number of DNN copyright protection methods have been proposed. However, most of the existing watermarking methods focus on verifying the copyright of the model, which do not support the authentication and management of users' fingerprints, thus can not satisfy the requirements of commercial copyright protection. In addition, the query modification attack which was proposed recently can invalidate most of the existing backdoor-based watermarking methods. To address these challenges, in this paper, we propose a method to protect the intellectual properties of DNN models by using an additional class and steganographic images. Specifically, we use a set of watermark key samples to embed an additional class into the DNN, so that the watermarked DNN will classify the watermark key sample as the predefined additional class in the copyright verification stage. We adopt the least significant bit (LSB) image steganography to embed users' fingerprints into watermark key images. Each user will be assigned with a unique fingerprint image so that the user's identity can be authenticated later. Experimental results demonstrate that, the proposed method can protect the copyright of DNN models effectively. On Fashion-MNIST and CIFAR-10 datasets, the proposed method can obtain 100% watermark accuracy and 100% fingerprint authentication success rate. In addition, the proposed method is demonstrated to be robust to the model fine-tuning attack, model pruning attack, and the query modification attack. Compared with three existing watermarking methods (the logo-based, noise-based, and adversarial frontier stitching watermarking methods), the proposed method has better performance on watermark accuracy and robustness against the query modification attack.
翻译:最近,关于保护深神经网络(DNN)的知识产权(IP)的研究引起了严重的关注。一些DNN版权保护方法已经提出。然而,大多数现有的水标记方法侧重于核实模型版权的版权,这种版权并不支持用户指纹的认证和管理,因此无法满足商业版权保护的要求。此外,最近提出的调试攻击可以使大多数现有的以后门为基础的水标记方法失效。为了应对这些挑战,我们在本文件中提议了一种方法,通过使用更多的类和有色图像来保护DNN模型的知识产权。但具体地说,我们使用一套水标记钥匙样本来将更多的类别嵌入DNNNN,这样,水标记的DNNNN就可以将水标记关键样品归类为版权核查阶段的预定义额外类别。我们采用了最不重要的(LSB)图像扫描方法,将用户的指纹嵌入以水标记攻击关键图像中。每个用户都会被指派一个独特的指纹图像,以便用户的精细读到Drial Rightal 。实验结果显示,100号中的拟议方法可以保护FMAR的版权方法。