skip to main content
10.1145/3507657.3528558acmconferencesArticle/Chapter ViewAbstractPublication PageswisecConference Proceedingsconference-collections
short-paper
Public Access

BiasHacker: Voice Command Disruption by Exploiting Speaker Biases in Automatic Speech Recognition

Published: 16 May 2022 Publication History

Abstract

Modern speech recognition systems that are widely deployed today still suffer from known gender and racial biases. In this work, we demonstrate the potential to exploit the existing biases in these systems to achieve a new attack goal. We consider the potential for command disruption by an attacker that can be conducted in a manner that allows for access and control of a victim's voice assistant device. We present a novel attack, BiasHacker, which crafts specialized chatter noise to exploit racial and gender biases in speech recognition systems for the purposes of command disruption. Our experimental results confirm both racial and gender bias that is still present in the speech recognition systems of two modern smart speaker devices. We also evaluated the effectiveness of three types of chatter noise (American English (AE)-Male, Nigerian-Female, Korean-Female) for disruption and demonstrate that the AE-Male chatter is consistently more successful. Comparing the average success rate of each chatter type, in scenarios where disruption was achieved, we find that when targeting the Google Home mini smart speaker, the AE-Male chatter noise increases average disruption success compared to the Nigerian-Female and Korean-Female chatter noises by 112% and 121%, respectively. Also, when targeting the Amazon Echo Dot 2 the AE-Male chatter noise increases average disruption success compared to the Nigerian-Female and Korean-Female chatter noises by 42% and 69%, respectively.

References

[1]
Hadi Abdullah, Kevin Warren, Vincent Bindschaedler, Nicolas Papernot, and Patrick Traynor. 2021. SoK: The Faults in our ASRs: An Overview of Attacks against Automatic Speech Recognition and Speaker Identification Systems. 2021 IEEE Symposium on Security and Privacy (SP), 730--747.
[2]
Nicholas Carlini, Pratyush Mishra, Tavish Vaidya, Yuankai Zhang, Michael E. Sherr, Clay Shields, David A. Wagner, and Wenchao Zhou. 2016. Hidden Voice Commands. In USENIX Security Symposium.
[3]
Varun Chandrasekaran, Kassem Fawaz, Bilge Mutlu, and Suman Banerjee. 2018. Characterizing privacy perceptions of voice assistants: A technology probe study. arXiv preprint arXiv:1812.00263 (2018).
[4]
Peng Cheng, Ibrahim Ethem Bagci, Jeff Yan, and Utz Roedig. 2018. Towards reactive acoustic jamming for personal voice assistants. In Proceedings of the 2nd International Workshop on Multimedia Privacy and Security. 12--17.
[5]
Siyuan Feng, Olya Kudina, Bence Mark Halpern, and Odette Scharenborg. 2021. Quantifying Bias in Automatic Speech Recognition. ArXiv abs/2103.15122 (2021).
[6]
Mahault Garnerin, Solange Rossato, and Laurent Besacier. 2019. Gender Representation in French Broadcast Corpora and Its Impact on ASR Performance. Proceedings of the 1st International Workshop on AI for Smart TV Content Production, Access and Delivery (2019).
[7]
Mahault Garnerin, Solange Rossato, and Laurent Besacier. 2020. Gender Representation in Open Source Speech Resources. In LREC.
[8]
Jan Gorisch, Michael Gref, and Thomas C. Schmidt. 2020. Using Automatic Speech Recognition in Spoken Corpus Curation. In LREC.
[9]
Chunxi Liu, Michael Picheny, Leda Sari, Pooja Chitkara, Alex Xiao, Xiaohui Zhang, Mark Chou, Andres Alvarado, Caner Hazirbas, and Yatharth Saraf. 2021. Towards Measuring Fairness in Speech Recognition: Casual Conversations Dataset Transcriptions. ArXiv abs/2111.09983 (2021).
[10]
Joshua L. Martin. 2021. Spoken Corpora Data, Automatic Speech Recognition, and Bias Against African American Language: The case of Habitual 'Be'. Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency (2021).
[11]
Cade Metz. 2020. There Is a Racial Divide in Speech-Recognition Systems, Researchers Say. https://www.nytimes.com/2020/03/23/technology/speechrecognition- bias-apple-amazon-google.html
[12]
Josh Meyer, Lindy Rauchenstein, Joshua D. Eisenberg, and Nicholas Howell. 2020. Artie Bias Corpus: An Open Dataset for Detecting Demographic Bias in Speech Applications. In LREC.
[13]
Taekkyung Oh, William Aiken, and Hyoungshick Kim. 2018. Hey Siri -- Are You There?: Jamming of Voice Commands Using the Resonance Effect (Work-in-Progress). 2018 International Conference on Software Security and Assurance (ICSSA) (2018), 73--76.
[14]
Mishaela Robison. 2020. Voice assistants have a gender bias problem. What can we do about it? https://www.brookings.edu/blog/techtank/2020/12/09/voiceassistants- have-a-gender-bias-problem-what-can-we-do-about-it/
[15]
Takeshi Sugawara, Benjamin Cyr, Sara Rampazzi, Daniel Genkin, and Kevin Fu. 2020. Light Commands: Laser-Based Audio Injection Attacks on Voice-Controllable Systems. In USENIX Security Symposium.
[16]
Rachael Tatman and Conner Kasten. 2017. Effects of Talker Dialect, Gender & Race on Accuracy of Bing Speech and YouTube Automatic Captions. In Proc. Interspeech 2017. 934--938. https://doi.org/10.21437/Interspeech.2017--1746
[17]
Eva Vanmassenhove, Christian Hardmeier, and Andy Way. 2018. Getting Gender Right in Neural Machine Translation. ArXiv abs/1909.05088 (2018).
[18]
Kyle Wiggers. 2021. Study finds that even the best speech recognition systems exhibit bias. https://venturebeat.com/2021/04/01/study-finds-that-even-thebest- speech-recognition-systems-exhibit-bias/
[19]
Qiben Yan, Kehai Liu, Qin Zhou, Hanqing Guo, and Ning Zhang. 2020. SurfingAttack: Interactive Hidden Attack on Voice Assistants Using Ultrasonic Guided Waves. In NDSS.
[20]
Guoming Zhang, Chen Yan, Xiaoyu Ji, Tianchen Zhang, Taimin Zhang, and Wenyuan Xu. 2017. DolphinAttack: Inaudible Voice Commands. In Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security (CCS '17). Association for Computing Machinery, New York, NY, USA, 103--117. https://doi.org/10.1145/3133956.3134052

Cited By

View all
  • (2024)End-Users Know Best: Identifying Undesired Behavior of Alexa Skills Through User Review AnalysisProceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies10.1145/36785178:3(1-28)Online publication date: 9-Sep-2024
  • (2023)Augmented Datasheets for Speech Datasets and Ethical Decision-MakingProceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency10.1145/3593013.3594049(881-904)Online publication date: 12-Jun-2023
  • (2023)Envisioning Equitable Speech Technologies for Black Older AdultsProceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency10.1145/3593013.3594005(379-388)Online publication date: 12-Jun-2023

Index Terms

  1. BiasHacker: Voice Command Disruption by Exploiting Speaker Biases in Automatic Speech Recognition

      Recommendations

      Comments

      Information & Contributors

      Information

      Published In

      cover image ACM Conferences
      WiSec '22: Proceedings of the 15th ACM Conference on Security and Privacy in Wireless and Mobile Networks
      May 2022
      314 pages
      ISBN:9781450392167
      DOI:10.1145/3507657
      • General Chair:
      • Murtuza Jadliwala,
      • Program Chairs:
      • Yongdae Kim,
      • Alexandra Dmitrienko
      Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

      Sponsors

      Publisher

      Association for Computing Machinery

      New York, NY, United States

      Publication History

      Published: 16 May 2022

      Permissions

      Request permissions for this article.

      Check for updates

      Author Tags

      1. bias
      2. command disruption
      3. speech recognition
      4. voice assistant

      Qualifiers

      • Short-paper

      Funding Sources

      Conference

      WiSec '22

      Acceptance Rates

      Overall Acceptance Rate 98 of 338 submissions, 29%

      Contributors

      Other Metrics

      Bibliometrics & Citations

      Bibliometrics

      Article Metrics

      • Downloads (Last 12 months)134
      • Downloads (Last 6 weeks)15
      Reflects downloads up to 07 Jan 2025

      Other Metrics

      Citations

      Cited By

      View all
      • (2024)End-Users Know Best: Identifying Undesired Behavior of Alexa Skills Through User Review AnalysisProceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies10.1145/36785178:3(1-28)Online publication date: 9-Sep-2024
      • (2023)Augmented Datasheets for Speech Datasets and Ethical Decision-MakingProceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency10.1145/3593013.3594049(881-904)Online publication date: 12-Jun-2023
      • (2023)Envisioning Equitable Speech Technologies for Black Older AdultsProceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency10.1145/3593013.3594005(379-388)Online publication date: 12-Jun-2023

      View Options

      View options

      PDF

      View or Download as a PDF file.

      PDF

      eReader

      View online with eReader.

      eReader

      Login options

      Media

      Figures

      Other

      Tables

      Share

      Share

      Share this Publication link

      Share on social media