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

计算机科学 感知 散列函数 计算机安全 认证(法律) 数字水印 语音识别 加密 人工智能 生物 神经科学
作者
Qiu-yu Zhang,Denghai Zhang,Fu-jiu Xu
出处
期刊:Multimedia Tools and Applications [Springer Science+Business Media]
被引量:5
标识
DOI:10.1007/s11042-021-10905-0
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.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
搜集达人的应助被Daangxi采纳,获得10
刚刚
lk发布了新的文献求助10
1秒前
所所的应助被困就睡觉采纳,获得10
1秒前
lyhh完成签到,获得积分10
1秒前
1秒前
英姑的应助被忧郁的鱿鱼采纳,获得10
1秒前
风趣的鼠标完成签到,获得积分10
2秒前
Color完成签到,获得积分10
2秒前
甜甜发布了新的文献求助10
2秒前
FashionBoy的应助被yy采纳,获得10
3秒前
墨辞完成签到,获得积分10
3秒前
3秒前
3秒前
3秒前
可爱觅松发布了新的文献求助10
3秒前
3秒前
田様的应助被明理鸿采纳,获得10
3秒前
秋风的应助被wyk采纳,获得10
3秒前
杀出个黎明举报求助违规成功
4秒前
Anonymous举报求助违规成功
4秒前
MchemG举报求助违规成功
4秒前
Ren的应助被朋友需要采纳,获得200
4秒前
脑洞疼的应助被lulululu采纳,获得10
4秒前
扶风阁主发布了新的文献求助10
4秒前
5秒前
七听的应助被番茄采纳,获得30
5秒前
5秒前
5秒前
ECCE发布了新的文献求助10
6秒前
mjq发布了新的文献求助10
6秒前
无情愫的应助被体贴洋葱采纳,获得10
7秒前
7秒前
7秒前
youyouyeah发布了新的文献求助10
7秒前
WBH36323发布了新的文献求助10
7秒前
逢坂大河发布了新的文献求助10
8秒前
8秒前
陶炳君完成签到 ,获得积分10
8秒前
任虎完成签到,获得积分10
8秒前
9秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1500
John McDowells Bildungstheorie 800
Analyses de reconnaissances de dettes passées devant les échevins d'Ypres (1249-1291) 600
Handbook of Pharmaceutical Excipients. 9th ed 400
Synthesis, Application and Future Perspectives of Smart Nano-materials - Part 1 400
Breaking the World 300
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8155737
求助须知:如何正确求助?哪些是违规求助? 9552018
关于积分的说明 21707687
捐赠科研通 7744923
什么是DOI,文献DOI怎么找? 3426177
关于科研通互助平台的介绍 2551229
邀请新用户注册赠送积分活动 2469949