基于秘密分享和SWT的数字音频水印算法  

Digital audio watermarking algorithm based on secret sharing and SWT

作　　者：李佳 马建芬 张朝霞 LI Jia;MA Jian-fen;ZHANG Zhao-xia(College of Information and Computer,Taiyuan University of Technology,Jinzhong 030600,China;College of Physics and Optoelectronics,Taiyuan University of Technology,Jinzhong 030600,China)

机构地区：[1]太原理工大学信息与计算机学院,山西晋中030600 [2]太原理工大学物理与光电工程学院,山西晋中030600

出　　处：《计算机工程与设计》2022年第3期616-623,共8页Computer Engineering and Design

基　　金：山西省重点研发计划基金项目(高新技术领域)(201803D121057);山西省面上自然基金项目(201701D121009);山西省回国留学人员科研基金项目(2017-031)。

摘　　要：为有效解决不可感知性、鲁棒性和有效载荷的权衡问题,以及水印信息的高安全性问题,提出一种基于秘密共享和平稳小波变换(SWT)的音频水印算法。利用Shamir的秘密共享方案对水印信息处理得到n份秘密信息,其中n-1份安全存储在区块链中,剩余一份嵌入在根据水印信息特征产生出的哈希码选定的浊音帧中。在频域内,通过SWT和Schur分解(SD)修正浊音帧的离散余弦变换(DCT)系数,将水印自适应地嵌入到从SD获得的正交矩阵的第一列元素中。实验结果表明,该算法具有较高的不可感知性,在低通滤波、重采样、重量化、MP3压缩和随机裁剪等各种信号处理攻击下具有很强的鲁棒性,有效载荷达到1.39 kbps。To solve the trade-off problem of imperceptibility,robustness and payload and the problem of high security of watermark information effectively,an audio watermarking algorithm based on secret sharing and stationary wavelet transform(SWT)was presented.Shamir’s secret sharing scheme was used to process the watermark information to obtain n pieces of secret information,of which n-1 copies were securely stored in the blockchain,and the remaining one was embedded in the selected voiced frames according to the hash code generated by the watermark information feature.In the frequency domain,by modifying the discrete cosine transform(DCT)coefficients of selected voiced frames through SWT and Schur decomposition(SD),the watermark was adaptively embedded in the first column element of the orthogonal matrix obtained from SD.Experimental results show that the proposed method has high imperceptibility and is strong robust to various signal processing attacks,such as filtering,re-sampling,requantization,MP3 compression and random cropping,the payload reaches 1.39 kbps.

关 键 词：Shamir的秘密分享方案 平稳小波变换 区块链 哈希码 浊音帧 SCHUR分解 离散余弦变换 信号处理攻击 

分 类 号：TP309[自动化与计算机技术—计算机系统结构]