A feasibility study of watermark embedding in RNN models
A feasibility study of watermark embedding in RNN models
复制标题
RNN 模型中水印嵌入的可行性研究
DOI：
10.1117/12.2626104
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Sakazawa Shigeyuki
中科院分区：
文献类型：
--
作者：
Matsumoto Kota;Sakazawa Shigeyuki
深度学习模型是使用大量的时间和数据创建的，因此成本非常高。因此，注意力集中在通过在学习模型中嵌入数字水印来保护权利的技术上。在这项工作中，我们针对递归神经网络（RNN）并在模型训练期间嵌入水印。很少有研究表明RNN训练模型嵌入水印的可能性。因此，在我们之前的研究中，我们已经证明了水印嵌入对于LSTM网络（一种RNN）生成的学习模型是可能的，并且已经进行了检测。在本文中，我们研究了水印嵌入到RNN的训练模型时对模型的影响。特别是，我们将进行实验，并讨论嵌入水印对任务的影响和增加嵌入水印的位数的影响的结果。
Deep learning models are created using a large amount of time and data, and are therefore very costly. Therefore, attention has been focused on technologies that protect rights by embedding digital watermarks in learning models. In this work, we target recurrent neural networks (RNNs) and embed watermarks during model training. There are few studies that show the possibility of watermark embedding for RNN training models. Therefore, in our previous research, we have shown that watermark embedding is possible for learning models generated by LSTM networks, a type of RNN, and have conducted detection. In this paper, we investigate the effect of watermarking on the model when it is embedded into the training model of RNN. In particular, we will conduct experiments and discuss the results regarding the impact of embedding watermarks on the task and the impact of increasing the number of bits embedded in the watermark.
DOI：
10.2307/495716
发表时间：
2020
期刊：
Gospel Patterns in Literature
影响因子：
--
作者：
Ernest Hemingway
通讯作者：
Ernest Hemingway