An encrypted speech authentication and tampering recovery method based on perceptual hashing

doi:10.1007/s11042-021-10905-0

	An encrypted speech authentication and tampering recovery method based on perceptual hashing
	Zhang, Qiu-yu; Zhang, Deng-hai; Xu, Fu-jiu
刊名	MULTIMEDIA TOOLS AND APPLICATIONS
	2021
卷号	80 期号:16 页码:24925-24948
关键词	Encrypted speech authentication Perceptual hashing Least square curve fitting Tampering location Tampering recovery
ISSN号	1380-7501
DOI	10.1007/s11042-021-10905-0
英文摘要	With the progress of speech retrieval technology in the cloud, it brings a lot of conveniences for speech user. Yet, the inquiry encrypted speech results from the speech retrieval system are faced with some secure issues to settle, such as integrity authentication and tampering recovery. In this paper, an encrypted speech authentication and tampering recovery method based on perceptual hashing is proposed. Firstly, the original speech is scrambled by Duffing mapping to construct an encrypted speech library in the cloud, through extracting product of uniform sub-band spectrum variance and spectral entropy of encrypted speech and constructing a perceptual hashing sequence to generate the hashing template of the cloud. From this, a one-to-one correspondence between the encrypted speech and perceptual hashing sequence is established. Secondly, the authentication digest of encrypted speech is extracted according to the inquiry result during the retrieval. Then, the authentication digest and the perceptual hashing sequence of the hashing template in the cloud are matched by the Hamming distance algorithm. Finally, for encrypted speech that fails authentication, tampering detection and location are performed, and the tampered samples are recovered by the least square curve fitting method. The simulation results show that the proposed method can extract the authentication digest directly in the encrypted speech, and the authentication digest not only has good discrimination and robustness, but it accurately locates the tampered area for malicious substitution and mute attacks. In addition, the proposed method can recover tampered speech signals in high quality without any extra information.
WOS研究方向	Computer Science ; Engineering
语种	英语
出版者	SPRINGER
WOS记录号	WOS:000639518700003
内容类型	期刊论文
源URL	[http://ir.lut.edu.cn/handle/2XXMBERH/148262]
专题	计算机与通信学院
作者单位	Lanzhou Univ Technol, Sch Comp & Commun, Lanzhou 730050, Peoples R China
推荐引用方式 GB/T 7714	Zhang, Qiu-yu,Zhang, Deng-hai,Xu, Fu-jiu. An encrypted speech authentication and tampering recovery method based on perceptual hashing[J]. MULTIMEDIA TOOLS AND APPLICATIONS,2021,80(16):24925-24948.
APA	Zhang, Qiu-yu,Zhang, Deng-hai,&Xu, Fu-jiu.(2021).An encrypted speech authentication and tampering recovery method based on perceptual hashing.MULTIMEDIA TOOLS AND APPLICATIONS,80(16),24925-24948.
MLA	Zhang, Qiu-yu,et al."An encrypted speech authentication and tampering recovery method based on perceptual hashing".MULTIMEDIA TOOLS AND APPLICATIONS 80.16(2021):24925-24948.