基于超声波非线性的汉语语音防窃听方法

高铭; 陈奕可; 陈佳彤; 肖甫; 韩劲松

doi:10.12263/DZXB.20240237

您当前的位置：

首页 >

文章列表页 >

基于超声波非线性的汉语语音防窃听方法

学术论文 | 更新时间：2025-12-08

- 基于超声波非线性的汉语语音防窃听方法
- Microphone Jamming Against Eavesdropping on Chinese Based on Ultrasonic Non-Linearity
- 电子学报 2025年53卷第3期页码：986-999
- 作者机构：
  
  1.南京邮电大学计算机学院/软件学院/网络空间安全学院，江苏南京210023
  2.浙江大学计算机科学与技术学院，浙江杭州310007
- 作者简介：
  
  高铭　男，1996年2月出生于江苏省连云港市.现为南京邮电大学计算机学院、软件学院、网络空间安全学院校长专聘教授.主要研究方向为智能感知、物联网安全与隐私保护.中国电子学会会员编号：E190159838M.E-mail: gaomingppm@njupt.edu.cn
  陈奕可　男，1998年1月出生于江苏省泰州市.现为浙江大学计算机科学与技术学院博士研究生.主要研究方向为物联网安全与无线感知.E-mail: chenyike@zju.edu.cn
  陈佳彤　男，2002年5月出生于重庆市.现为浙江大学计算机科学与技术学院硕士研究生.主要研究方向为物联网安全.E-mail: 3200105258@zju.edu.cn
  肖甫　男，1980年10月出生于湖南省邵阳市.现为南京邮电大学计算机学院、软件学院、网络空间安全学院教授、博士生导师.主要研究方向为物联网感知计算、物联网安全技术与数据中心网络.E-mail: xiaof@njupt.edu.cn
  韩劲松　男，1975年12月出生于山东省淄博市.现为浙江大学计算机科学与技术学院教授、博士生导师.主要研究方向为物联网安全、智能感知与隐私保护.E-mail: hanjinsong@zju.edu.cn
- 基金信息：
  
  国家杰出青年科学基金(62125203);国家自然科学基金(62372400)
- DOI：10.12263/DZXB.20240237
  中图分类号： TP393
- 收稿：2024-03-14，
  
  修回：2024-09-16，
  
  纸质出版：2025-03-25
- 稿件说明：
移动端阅览
高铭, 陈奕可, 陈佳彤, 等. 基于超声波非线性的汉语语音防窃听方法[J]. 电子学报, 2025, 53(03): 986-999.

GAO Ming, CHEN Yi-ke, CHEN Jia-tong, et al. Microphone Jamming Against Eavesdropping on Chinese Based on Ultrasonic Non-Linearity[J]. Acta Electronica Sinica, 2025, 53(03): 986-999.
高铭, 陈奕可, 陈佳彤, 等. 基于超声波非线性的汉语语音防窃听方法[J]. 电子学报, 2025, 53(03): 986-999. DOI：10.12263/DZXB.20240237

GAO Ming, CHEN Yi-ke, CHEN Jia-tong, et al. Microphone Jamming Against Eavesdropping on Chinese Based on Ultrasonic Non-Linearity[J]. Acta Electronica Sinica, 2025, 53(03): 986-999. DOI：10.12263/DZXB.20240237

摘要

语音隐私安全对于国家和个人信息安全至关重要.为了确保用户的语音隐私免受窃听，超声波录音干扰技术被广泛采用.此技术利用电子录音设备中的超声波非线性特征，在不影响正常交流的前提下，实现了高效且低成本的窃听录音干扰.然而，现有的语音防窃听技术仍存在安全隐患.由于以往技术仅采用简单的噪声掩盖技术，窃听者能够通过先进的去噪技术恢复语音信息，威胁语音隐私安全.特别地，这些方法的设计主要针对英语语音，对汉语语音的适用性有限.因此，针对汉语语音的隐私保护需求更为迫切.为提高超声波录音干扰的安全性和适用性，本文针对汉语语音隐私保护，设计了一种安全稳健的防窃听方法.本文分析汉语语音独特特征，以此为基础设计一种耦合噪声生成算法，该算法所生成的超声干扰噪声与汉语用户的语音信号紧密耦合、高度相关，因此难以分离，能够有效抵御各种去噪手段.本文充分考虑了窃听者的能力，实现不可恢复的录音干扰，在不影响用户听力及正常交流的情况下，构建了安全的防窃听方案，全面保护用户的语音隐私安全.为验证该方法的有效性，本文设计了超声波录音干扰原型系统.实验结果表明，在6 m的范围内，本文方法能够确保90%以上的用户语音内容无法被窃听者识读，为汉语语音隐私保护提供了强有力的技术支持.

Abstract

The privacy and security of speech are fundamental to both national and personal information security. To protect users’ speeches from being eavesdropped on

ultrasonic microphone jammers are widely utilized. These jammers utilize the nonlinear characteristics of ultrasound in digital recording devices to inject noise into microphones efficiently and cost-effectively

without disrupting normal communication or human hearing. However

existing microphone jammers are vulnerable. They merely introduce simple noise to mask speeches. As a result

eavesdroppers can employ advanced denoising techniques to recover speech information

posing a significant threat to speech privacy and security. Moreover

existing jammers have primarily been designed for English speech

limiting their applicability to Chinese speech. Therefore

there is an urgent need for privacy protection for Chinese speech. To enhance the security and adaptability of ultrasonic microphone jammers

this paper introduces a robust jammer for Chinese speech privacy protection. Based on the unique characteristics of Chinese phonetics

we design a coherent noise generation algorithm

which produces real-time ultrasound noise intimately coupled with the protected speech signal. This noise is designed to be difficult for adversaries to separate from the speech

ensuring that any attempts at eavesdropping will be frustrated. Comprehensively considering the capabilities of the potential adversaries adversary

our proposed jammer realizes the robust protection against eavesdropping. The generated noise cannot be removed by adversaries using state-of-the-art denoising techniques and is imperceptible to human hearing. Thereby

we comprehensively safeguard speech privacy and security. We develop a prototype of the proposed ultrasonic microphone jammer to validate its effectiveness. Experimental results demonstrate that over 90% of protected speeches remain unrecognizable to adversaries within a range of 6 meters under the protection of the proposed jammer

even if the adversary adopts state-of-the-art denoising techniques. Therefore

we provide robust technical support to protect Chinese speech privacy.

关键词

Keywords

references

盛玉雷 . 语音入口得加把“隐私锁” [N/OL ] .( 2019-08-13 )[ 2024-03-14 ] . http://opinion.people.com.cn/n1/2019/0813/c1003-31290817.html http://opinion.people.com.cn/n1/2019/0813/c1003-31290817.html .

THOMAS G . How to protect yourself from camera and microphone hacking [EB/OL ] .[ 2024-03-14 ] . https://www.consumerreports.org/electronics-computers/privacy/how-to-pr-otect-yourself-from-camera-and-microphone-hacking-a1010757171 https://www.consumerreports.org/electronics-computers/privacy/how-to-pr-otect-yourself-from-camera-and-microphone-hacking-a1010757171 .

WU H , QIAN W . Breaking Smart Speakers: We are Listening to You [R ] . Las Vegas : DEF CON Hacking Conference , 2018 .

SLOTTA D . Smart Speaker Market in China - Statistics & Facts [R ] . Germany : Statista , 2023 .

CHEN Y K , GAO M , LI Y M , et al . Big brother is listening: An evaluation framework on ultrasonic microphone jammers [C ] // Proceedings of the International Conference on Computer Communications . Piscataway : IEEE , 2022 : 1119 - 1128 .

ZHANG G M , YAN C , JI X Y , et al . DolphinAttack: Inaudible voice commands [C ] // Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security . New York : ACM , 2017 : 103 - 117 .

ROY N , HASSANIEH H , ROY CHOUDHURY R . BackDoor: Making microphones hear inaudible sounds [C ] // Proceedings of the 15th Annual International Conference on Mobile Systems, Applications, and Services . New York : ACM , 2017 : 2 - 14 .

CHEN Y X , LI H Y , et al . Wearable microphone jammi-ng [C ] // Proceedings of the Conference on Human Factors in Computing Systems . New York : ACM , 2020 : 1 - 12 .

LI L K , LIU M N , YAO Y G , et al . Patronus: Preventing unauthorized speech recordings with support for selective unscrambling [C ] // Proceedings of the 18th Conference on Embedded Networked Sensor Systems . New York : ACM , 2020 : 245 - 257 .

CHEN Y K , GAO M , LIU Y J , et al . Implement of a secure selective ultrasonic microphone jammer [J ] . CCF Transactions on Pervasive Computing and Interaction , 2021 , 3 ( 4 ): 367 - 377 .

MAKINO S , LEE T W , SAWADA H . Blind Speech Separation [M ] . Berlin : Springer , 2007 .

SUN K , CHEN C , ZHANG X Y . "Alexa, stop spying on me!": Speech privacy protection against voice assistan-ts [C ] // Proceedings of the Conference on Embedded Networked Sensor Systems . New York : ACM , 2020 : 298 - 311 .

GAO M , CHEN Y K , LIU Y J , et al . Cancelling speech signals for speech privacy protection against microphone eavesdropping [C ] // Proceedings of the 29th Annual International Conference on Mobile Computing and Networking . New York : ACM , 2023 : 1 - 16 .

HUANG P , WEI Y , CHENG P , et al . InfoMasker: Preventing eavesdropping using phoneme-based noise [C ] // Proceedings of the Network and Distributed System Security Symposium . Piscataway : IEEE , 2023 : 1 - 13 .

王力 . 汉语音韵,音韵学初步 [M ] . 北京 : 中华书局 , 2014 : 29 .

WANG X H , XU L . Speech perception in noise: Masking and unmasking [J ] . Journal of Otology , 2021 , 16 ( 2 ): 109 - 119 .

ZIEHE A , KAWANABE M , HARMELING S , et al . Blind separation of post-nonlinear mixtures using linearizing transformations and temporal decorrelation [J ] . Journal of Machine Learning Research , 2003 , 4 : 1319 - 1338 .

FREITAG L , STOJANOVIC M , SINGH S , et al . Analysis of channel effects on direct-sequence and frequency-hopped spread-spectrum acoustic communication [J ] . IEEE Journal of Oceanic Engineering , 2002 , 26 ( 4 ): 586 - 593 .

JUTTEN C , BABAIE-ZADEH M , HOSSEINI S . Three easy ways for separating nonlinear mixtures? [J ] . Signal Processing , 2004 , 84 ( 2 ): 217 - 229 .

ALMEIDA L B . Linear and nonlinear ICA based on mutual information [C ] // Proceedings of the Adaptive Systems for Signal Processing, Communications, and Control Symposium . Piscataway : IEEE , 2002 : 117 - 122 .

TALEB A . A generic framework for blind source separation in structured nonlinear models [J ] . IEEE Transactions on Signal Processing , 2002 , 50 ( 8 ): 1819 - 1830 .

OpenSLR . ST-CMDS-20170001_ 1 , Free ST Chinese Man-darinCorpus[EB/OL ] . ( 2022-08-29 )[ 2024-03-24 ] . https:// openslr.org/38/ https://openslr.org/38/ .

JIA Y , ZHANG Y , WEISS R , et al . Transfer learning from speaker verification to multispeaker text-to-speech synthesis [J ] . Advances in Neural Information Processing Systems , 2018 , 31 : 4485 - 4495 .

FAN Y , KANG J W , LI L T , et al . CN-celeb: A challenging Chinese speaker recognition dataset [C ] // IEEE International Conference on Acoustics, Speech and Signal Processing . Piscataway : IEEE , 2020 : 7604 - 7608 .

SAKOE H , CHIBA S . Dynamic programming algorithm optimization for spoken word recognition [J ] . IEEE Transactions on Acoustics, Speech, and Signal Processing , 1978 , 26 ( 1 ): 43 - 49 .

OTSU N . A threshold selection method from gray-level histograms [J ] . IEEE Transactions on Systems, Man, and Cybernetics , 1979 , 9 ( 1 ): 62 - 66 .

DUCK F A . Medical and non-medical protection standards for ultrasound and infrasound [J ] . Progress in Biophysics and Molecular Biology , 2007 , 93 ( 1-3 ): 176 - 191 .

An artificial intelligence platform focusing on intelligent speech interaction which provides solutions for developers [EB/OL ] . [ 2024-03-14 ] . https://www.xfyun.cn https://www.xfyun.cn .

Nl 8590687 . ASRT: a DL-based Chinese ASR system [EB/OL ] . ( 2022-08-29 )[ 2024-03-14 ] . https://www.xfyun.cn https://www.xfyun.cn .

OJA E , YUAN Z J . The fastICA algorithm revisited: Convergence analysis [J ] . IEEE Transactions on Neural Networks , 2006 , 17 ( 6 ): 1370 - 1381 .

HE Y T , BIAN J Y , TONG X Y , et al . Canceling inaudible voice commands against voice control systems [C ] // The 25th Annual International Conference on Mobile Com-puting and Networking . New York : ACM , 2019 : 1 - 15 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据