column

BackDoor: Sounds that a microphone can record, but that humans can't hear

Authors:

Nirupam Roy,

Haitham Hassanieh,

Romit Roy ChoudhuryAuthors Info & Claims

GetMobile: Mobile Computing and Communications, Volume 21, Issue 4

Pages 25 - 29

https://doi.org/10.1145/3191789.3191799

Published: 28 February 2018 Publication History

Get Access

Abstract

Microphones are like human ears. If we play an audible sound, both humans and microphones will be able to hear it. We design sound that appears just as any other sound to microphones, but remains inaudible to humans. This sound can be regulated to carry data bits, thereby enabling an acoustic (but inaudible) communication channel to hundreds of smart devices that already have built-in microphones. Other applications include jamming spy microphones in the environment, live watermarking of music in a concert, and even threats like acoustic denial-of-service (DoS) attacks on phone calls or inaudible command attacks on voice-enabled devices.

References

[1]

Chirp technology. http://www.chirp.io.

Google Scholar

[2]

Iannucci, P. A., Netravali, R., Goyal, A. K., and Balakrishnan, H. Room-area networks. In Proceedings of the 14th ACM Workshop on Hot Topics in Networks (2015), ACM, p. 9.

Digital Library

Google Scholar

[3]

B. Zhang et al., "PriWhisper: Enabling keyless secure acoustic communication for smartphones," IEEE Internet of Things Journal, vol. 1, no. 1, Feb. 2014, pp. 33--45.

Crossref

Google Scholar

[4]

Nandakumar, R., Chintalapudi, K. K., Padmanabhan, V., and Venkatesan, R. Dhwani: secure peer-to-peer acoustic nfc. In ACM SIGCOMM Computer Communication Review (2013), vol. 43, pp. 63--74.

Digital Library

Google Scholar

[5]

Cmu sphinx. http://cmusphinx.sourceforge.net.

Google Scholar

[6]

Perez, J. P. A., Pueyo, S. C., and Lopez, B. C.Agc fundamentals. In Automatic Gain Control. (Springer, 2011), pp. 13--28.

Crossref

Google Scholar

[7]

Shannon, C.E. "Communication in the presence of noise." Proceedings of the IRE. 1949 Jan.; 37(1):10--21.

Google Scholar

Cited By

View all

Liu TWang CLi ZHuang MXu WLin F(2024)Wavoice: An mmWave-Assisted Noise-Resistant Speech Recognition SystemACM Transactions on Sensor Networks10.1145/359745720:4(1-29)Online publication date: 11-May-2024
https://dl.acm.org/doi/10.1145/3597457
Mengara OAvila AFalk T(2024)Backdoor Attacks to Deep Neural Networks: A Survey of the Literature, Challenges, and Future Research DirectionsIEEE Access10.1109/ACCESS.2024.335581612(29004-29023)Online publication date: 2024
https://doi.org/10.1109/ACCESS.2024.3355816
Renz ANeff TBaldauf MMaier E(2023)Authentication methods for voice services on smart speakers – a multi-method study on perceived security and ease of usei-com10.1515/icom-2022-003922:1(67-81)Online publication date: 29-Mar-2023
https://doi.org/10.1515/icom-2022-0039
Show More Cited By

Recommendations

The Silent Manipulator: A Practical and Inaudible Backdoor Attack against Speech Recognition Systems
MM '23: Proceedings of the 31st ACM International Conference on Multimedia

Backdoor Attacks have been shown to pose significant threats to automatic speech recognition systems (ASRs). Existing success largely assumes backdoor triggering in the digital domain, or the victim will not notice the presence of triggering sounds in ...
BackDoor: Making Microphones Hear Inaudible Sounds
MobiSys '17: Proceedings of the 15th Annual International Conference on Mobile Systems, Applications, and Services

Consider sounds, say at 40kHz, that are completely outside the human's audible range (20kHz), as well as a microphone's recordable range (24kHz). We show that these high frequency sounds can be designed to become recordable by unmodified microphones, ...
Detecting acoustic backdoor transmission of inaudible messages using deep learning
WiseML '20: Proceedings of the 2nd ACM Workshop on Wireless Security and Machine Learning

The novel secret inaudible acoustic communication channel [11], referred to as the BackDoor channel, is a method of embedding inaudible signals in acoustic data that is likely to be processed by a trained deep neural net. In this paper we perform ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image GetMobile: Mobile Computing and Communications

GetMobile: Mobile Computing and Communications Volume 21, Issue 4

December 2017

30 pages

ISSN:2375-0529

EISSN:2375-0537

DOI:10.1145/3191789

Editor:
Eyal de Lara
University of Toronto

Issue’s Table of Contents

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 28 February 2018

Published in SIGMOBILE-GETMOBILE Volume 21, Issue 4

Check for updates

Qualifiers

Column

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

11
Total Citations
View Citations
251
Total Downloads

Downloads (Last 12 months)16
Downloads (Last 6 weeks)1

Reflects downloads up to 30 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

View all

Liu TWang CLi ZHuang MXu WLin F(2024)Wavoice: An mmWave-Assisted Noise-Resistant Speech Recognition SystemACM Transactions on Sensor Networks10.1145/359745720:4(1-29)Online publication date: 11-May-2024
https://dl.acm.org/doi/10.1145/3597457
Mengara OAvila AFalk T(2024)Backdoor Attacks to Deep Neural Networks: A Survey of the Literature, Challenges, and Future Research DirectionsIEEE Access10.1109/ACCESS.2024.335581612(29004-29023)Online publication date: 2024
https://doi.org/10.1109/ACCESS.2024.3355816
Renz ANeff TBaldauf MMaier E(2023)Authentication methods for voice services on smart speakers – a multi-method study on perceived security and ease of usei-com10.1515/icom-2022-003922:1(67-81)Online publication date: 29-Mar-2023
https://doi.org/10.1515/icom-2022-0039
Garg NShahid IAvllazagaj EHill JHan JRoy N(2023)ThermWareProceedings of the 24th International Workshop on Mobile Computing Systems and Applications10.1145/3572864.3580339(81-88)Online publication date: 22-Feb-2023
https://dl.acm.org/doi/10.1145/3572864.3580339
Renz ABaldauf MMaier EAlt F(2022)Alexa, It’s Me! An Online Survey on the User Experience of Smart Speaker AuthenticationProceedings of Mensch und Computer 202210.1145/3543758.3543765(14-24)Online publication date: 4-Sep-2022
https://dl.acm.org/doi/10.1145/3543758.3543765
Bai YGarg NRoy NBulusu NAryafar EBalasubramanian ASong J(2022)SPiDRProceedings of the 20th Annual International Conference on Mobile Systems, Applications and Services10.1145/3498361.3539775(99-113)Online publication date: 27-Jun-2022
https://dl.acm.org/doi/10.1145/3498361.3539775
Chandrasekaran VBanerjee SMutlu BFawaz KChiasson S(2021)PowerCut and obfuscatorProceedings of the Seventeenth USENIX Conference on Usable Privacy and Security10.5555/3563572.3563600(535-551)Online publication date: 9-Aug-2021
https://dl.acm.org/doi/10.5555/3563572.3563600
Liu TGao MLin FWang CBa ZHan JXu WRen K(2021)WavoiceProceedings of the 19th ACM Conference on Embedded Networked Sensor Systems10.1145/3485730.3485945(97-110)Online publication date: 15-Nov-2021
https://dl.acm.org/doi/10.1145/3485730.3485945
Mhaidli AVenkatesh MZou YSchaub F(2020)Listen Only When Spoken To: Interpersonal Communication Cues as Smart Speaker Privacy ControlsProceedings on Privacy Enhancing Technologies10.2478/popets-2020-00262020:2(251-270)Online publication date: 8-May-2020
https://doi.org/10.2478/popets-2020-0026
Huang YObada-Obieh BBeznosov KBernhaupt RMueller FVerweij DAndres JMcGrenere JCockburn AAvellino IGoguey ABjørn PZhao SSamson BKocielnik R(2020)Amazon vs. My Brother: How Users of Shared Smart Speakers Perceive and Cope with Privacy RisksProceedings of the 2020 CHI Conference on Human Factors in Computing Systems10.1145/3313831.3376529(1-13)Online publication date: 21-Apr-2020
https://dl.acm.org/doi/10.1145/3313831.3376529
Show More Cited By

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Cited By

Recommendations

The Silent Manipulator: A Practical and Inaudible Backdoor Attack against Speech Recognition Systems

BackDoor: Making Microphones Hear Inaudible Sounds

Detecting acoustic backdoor transmission of inaudible messages using deep learning