[go: up one dir, main page]
More Web Proxy on the site http://driver.im/ Skip to main content
Springer Nature Link
Log in

Adjust-free adversarial example generation in speech recognition using evolutionary multi-objective optimization under black-box condition

  • Original Article
  • Published:
Artificial Life and Robotics Aims and scope Submit manuscript

Abstract

This paper proposes a black-box adversarial attack method to automatic speech recognition systems. Some studies have attempted to attack neural networks for speech recognition; however, these methods did not consider the robustness of generated adversarial examples against timing lag with a target speech. The proposed method in this paper adopts Evolutionary Multi-objective Optimization (EMO) that allows it generating robust adversarial examples under black-box scenario. Experimental results showed that the proposed method successfully generated adjust-free adversarial examples, which are sufficiently robust against timing lag so that an attacker does not need to take the timing of playing it against the target speech.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
£29.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (United Kingdom)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

Notes

  1. Tested 60 adversarial examples can be available at https://mediaeng.ics.kagoshima-u.ac.jp/adjustFreeAE.html.

  2. Pairred t test with 95% confidence level was performed for each comparison.

References

  1. Alzantot M, Balaji B, Srivastava M (2018) Did you hear that? adversarial examples against automatic speech recognition. arXiv preprint arXiv:1801.00554

  2. Athalye A, Engstrom L, Ilyas Aa (2017) Synthesizing robust adversarial examples. arXiv preprint arXiv:1707.07397

  3. Carlini N, Wagner D (2018) Audio adversarial examples: targeted attacks on speech-to-text. In: 2018 IEEE security and privacy workshops (SPW), pp 1–7. IEEE

  4. Goodfellow IJ, Shlens J, Szegedy C (2014) Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572

  5. Ittichaichareon C, Suksri S, Yingthawornsuk T (2012) Speech recognition using mfcc. In: International conference on computer graphics, simulation and modeling, pp 135–138

  6. Khare S, Aralikatte R, Mani S (2018) Adversarial black-box attacks on automatic speech recognition systems using multi-objective evolutionary optimization. arXiv preprint arXiv:1811.01312

  7. Ono S, Hirotani Y, Nakayama S (2009) A memetic algorithm for robust optimal solution search-hybridization of multi-objective genetic algorithm and quasi-newton method. Int J Innov Comput Inf Control 5(12):5011–5019

    Google Scholar 

  8. Qin Y, Carlini N, Goodfellow IA (2019) Imperceptible, robust, and targeted adversarial examples for automatic speech recognition. arXiv preprint arXiv:1903.10346

  9. Sainath TN, Parada C (2015) Convolutional neural networks forsmall-footprint keyword spotting. In: Proceedings of the sixteenth annual conference of the international speech communication association

  10. Storn R, Price K (1997) Differential evolution-a simple and efficient heuristic for global optimization over continuous spaces. J Global Optim 11(4):341–359

    Article  MathSciNet  Google Scholar 

  11. Su J, Vargas DV, Sakurai K (2019) One pixel attack for fooling deep neural networks. IEEE Trans Evol Comput 23:828–41

    Article  Google Scholar 

  12. Suzuki T, Takeshita S, Ono S (2019) Adversarial example generation using evolutionary multi-objective optimization. In: 2019 IEEE Congress on evolutionary computation (CEC), pp 2136–2144. IEEE

  13. Taori R, Kamsetty A, Chu B (2019) Targeted adversarial examples for black box audio systems. In: 2019 IEEE security and privacy workshops (SPW), pp 15–20. IEEE

  14. Yakura H, Sakuma J (2018) Robust audio adversarial example for a physical attack. arXiv preprint arXiv:1810.11793

  15. Zhang Q, Liu W, Li H (2009) The performance of a new version of moea/d on cec09 unconstrained mop test instances. In: 2009 IEEE congress on evolutionary computation, pp 203–208. IEEE

Download references

Acknowledgements

This study was partially supported by the Kayamori Foundation of Informational Science Advancement.

Author information

Authors and Affiliations

  1. Department of Information Science and Biomedical Engineering, Graduate School of Science and Engineering, Kagoshima University, Kagoshima, Japan

    Shoma Ishida & Satoshi Ono

Authors
  1. Shoma Ishida
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Satoshi Ono
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Shoma Ishida.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

This work was presented in part at the 25th International Symposium on Artificial Life and Robotics (Beppu, Oita, January 22–24, 2020).

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ishida, S., Ono, S. Adjust-free adversarial example generation in speech recognition using evolutionary multi-objective optimization under black-box condition. Artif Life Robotics 26, 243–249 (2021). https://doi.org/10.1007/s10015-020-00671-x

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10015-020-00671-x

Keywords

Search

Navigation