Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
134 tokens/sec
GPT-4o
10 tokens/sec
Gemini 2.5 Pro Pro
47 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Protecting Voice-Controlled Devices against LASER Injection Attacks (2310.09404v1)

Published 13 Oct 2023 in eess.AS

Abstract: Voice-Controllable Devices (VCDs) have seen an increasing trend towards their adoption due to the small form factor of the MEMS microphones and their easy integration into modern gadgets. Recent studies have revealed that MEMS microphones are vulnerable to audio-modulated laser injection attacks. This paper aims to develop countermeasures to detect and prevent laser injection attacks on MEMS microphones. A time-frequency decomposition based on discrete wavelet transform (DWT) is employed to decompose microphone output audio signal into n + 1 frequency subbands to capture photo-acoustic related artifacts. Higher-order statistical features consisting of the first four moments of subband audio signals, e.g., variance, skew, and kurtosis are used to distinguish between acoustic and photo-acoustic responses. An SVM classifier is used to learn the underlying model that differentiates between an acoustic- and laser-induced (photo-acoustic) response in the MEMS microphone. The proposed framework is evaluated on a data set of 190 audios, consisting of 19 speakers. The experimental results indicate that the proposed framework is able to correctly classify $98\%$ of the acoustic- and laser-induced audio in a random data partition setting and $100\%$ of the audio in speaker-independent and text-independent data partition settings.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (29)
  1. R. Bogue, “Recent developments in mems sensors: A review of applications, markets and technologies,” Sensor review, vol. 33, no. 4, pp. 300–304, 2013.
  2. S. A. Zawawi, A. A. Hamzah, B. Y. Majlis, and F. Mohd-Yasin, “A review of mems capacitive microphones,” Micromachines, vol. 11, no. 5, p. 484, 2020.
  3. M. E. Abidi et al., “Development of voice control and home security for smart home automation,” in 2018 7th Int. Conf. on Computer and Communication Engineering (ICCCE).   IEEE, 2018, pp. 1–6.
  4. S. Sen, S. Chakrabarty, R. Toshniwal, and A. Bhaumik, “Design of an intelligent voice controlled home automation system,” Int. Journal of Computer Applications, vol. 121, no. 15, 2015.
  5. “Amazon Alexa Voice AI — Alexa Developer Official Site — developer.amazon.com,” https://developer.amazon.com/en-US/alexa, [Accessed 14-Jul-2023].
  6. Y. Zou, X. Liu, H. Xu, Y. Hou, and J. Qi, “Design of intelligent customer service report system based on automatic speech recognition and text classification,” in E3S Web of Confs., vol. 295.   EDP Sciences, 2021.
  7. M. Zhang, “Artificial intelligence and application in finance,” in Proc. of the 2020 11th Int. Conf. on E-Education, E-Business, E-Management, and E-Learning, 2020, pp. 317–322.
  8. T. Sugawara, B. Cyr, S. Rampazzi, D. Genkin, and K. Fu, “Light commands: Laser-based audio injection attacks on voice-controllable systems,” in 29th USENIX Security Symposium (USENIX Security 20), 2020, pp. 2631–2648.
  9. M. R. Kamble, H. B. Sailor, H. A. Patil, and H. Li, “Advances in anti-spoofing: from the perspective of asvspoof challenges,” APSIPA Trans. on Signal and Information Processing, vol. 9, p. e2, 2020.
  10. A. Nautsch et al., “Asvspoof 2019: spoofing countermeasures for the detection of synthesized, converted and replayed speech,” IEEE Trans. on Biometrics, Behavior, and Identity Science, vol. 3, no. 2, pp. 252–265, 2021.
  11. B. Balamurali, K. E. Lin, S. Lui, J.-M. Chen, and D. Herremans, “Toward robust audio spoofing detection: A detailed comparison of traditional and learned features,” IEEE Access, vol. 7, pp. 84 229–84 241, 2019.
  12. M. Todisco et al., “ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detection,” in Proc. Interspeech 2019, 2019, pp. 1008–1012.
  13. R. K. Das, J. Yang, and H. Li, “Long range acoustic and deep features perspective on asvspoof 2019,” in 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).   IEEE, 2019, pp. 1018–1025.
  14. W. Cai, H. Wu, D. Cai, and M. Li, “The dku replay detection system for the asvspoof 2019 challenge: On data augmentation, feature representation, classification, and fusion,” arXiv preprint arXiv:1907.02663, 2019.
  15. Y. Yang et al., “The sjtu robust anti-spoofing system for the asvspoof 2019 challenge.” in Interspeech, 2019, pp. 1038–1042.
  16. M. Adiban, H. Sameti, and S. Shehnepoor, “Replay spoofing countermeasure using autoencoder and siamese networks on asvspoof 2019 challenge,” Computer Speech & Language, vol. 64, p. 101105, 2020.
  17. P. Mishra, “A vector quantization approach to speaker recognition,” in Proc. of Int. conf. on innovation & research in technology for sustainable development (ICIRT 2012), vol. 1, 2012, p. 152.
  18. D. Reynolds, T. Quatieri, and R. Dunn, “Speaker verification using adapted gaussian mixture models,” Digital signal processing, vol. 10, pp. 19–41, 2000.
  19. D. Matrouf, N. Scheffer, B. G. Fauve, and J.-F. Bonastre, “A straightforward and efficient implementation of the factor analysis model for speaker verification.” in Interspeech, 2007, pp. 1242–1245.
  20. M. Sahidullah, T. Kinnunen, and C. Hanilçi, “A comparison of features for synthetic speech detection,” 2015.
  21. Y. Qian, N. Chen, and K. Yu, “Deep features for automatic spoofing detection,” Speech Communication, vol. 85, pp. 43–52, 2016.
  22. H. Yu, Z.-H. Tan, Z. Ma, R. Martin, and J. Guo, “Spoofing detection in automatic speaker verification systems using dnn classifiers and dynamic acoustic features,” IEEE trans. on neural networks and learning systems, vol. 29, no. 10, pp. 4633–4644, 2017.
  23. N. Chen, Y. Qian, H. Dinkel, B. Chen, and K. Yu, “Robust deep feature for spoofing detection—the sjtu system for asvspoof 2015 challenge,” in Sixteenth Annual Conf. of the Int. Speech Comm. Asso., 2015.
  24. Z. Chen, Z. Xie, W. Zhang, and X. Xu, “Resnet and model fusion for automatic spoofing detection.” in Interspeech, 2017, pp. 102–106.
  25. S. Manohar and D. Razansky, “Photoacoustics: a historical review,” Advances in optics and photonics, vol. 8, no. 4, pp. 586–617, 2016.
  26. R. M. Sullenberger, S. Kaushik, and C. M. Wynn, “Photoacoustic communications: delivering audible signals via absorption of light by atmospheric h 2 o,” Optics Letters, vol. 44, no. 3, pp. 622–625, 2019.
  27. B. Cyr, T. Sugawara, and K. Fu, “Why lasers inject perceived sound into mems microphones: Indications and contraindications of photoacoustic and photoelectric effects,” in 2021 IEEE Sensors.   IEEE, 2021, pp. 1–4.
  28. R. Djerv, “Investigation of light and ultrasound injected signals in microphones,” 2021.
  29. F. Pedregosa et al., “Scikit-learn: Machine learning in Python,” Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011.
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now