arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2012.14171cs.CRcs.AI
收藏

基于深度神经网络的小波变换抖动调制水印

Spread-Transform Dither Modulation Watermarking of Deep Neural Network

Southwest Jiaotong University(西南交通大学);University of Siena(锡耶纳大学)

Yue Li, Benedetta Tondi, Mauro Barni

摘要:

DNN水印作为保护与DNN模型相关联的知识产权的合适手段正受到越来越多的关注。到目前为止提出的几种方法受到流行的扩频(SS)范例的启发,根据该范例,水印比特被嵌入到DNN模型的权重到伪随机序列上的投影中。在本文中,我们提出了一种新的DNN水印算法,利用水印与边信息范例,以减少水印的突兀性,并增加其有效载荷。特别是,新方案利用的主要思想ST-DM(扩频变换抖动调制)水印,以提高性能的一个最近提出的算法的基础上,传统的SS。我们进行了实验,通过应用所提出的计划水印不同的模型,证明了它的能力,以提供更高的有效载荷与较低的影响网络的准确性比基线方法的基础上,传统的SS,同时保持令人满意的水平的鲁棒性。

英文摘要:

DNN watermarking is receiving an increasing attention as a suitable mean to protect the Intellectual Property Rights associated to DNN models. Several methods proposed so far are inspired to the popular Spread Spectrum (SS) paradigm according to which the watermark bits are embedded into the projection of the weights of the DNN model onto a pseudorandom sequence. In this paper, we propose a new DNN watermarking algorithm that leverages on the watermarking with side information paradigm to decrease the obtrusiveness of the watermark and increase its payload. In particular, the new scheme exploits the main ideas of ST-DM (Spread Transform Dither Modulation) watermarking to improve the performance of a recently proposed algorithm based on conventional SS. The experiments we carried out by applying the proposed scheme to watermark different models, demonstrate its capability to provide a higher payload with a lower impact on network accuracy than a baseline method based on conventional SS, while retaining a satisfactory level of robustness.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑