SJT | Scientific Journal of Technology
← Back to Volume 8, Issue 9

Anti-Spoofing Evaluation Benchmark and Layered Defense Strategy for In-Cabin Voiceprint Payment under Voice Cloning Attacks

Benyin Wu, Ruizhi Feng, Ziyi Wang, Yihong Qin
Vol. 8, No. 9, pp. 22-28, 2026 DOI: 10.54691/c57jbf30 September 21, 2026
Download PDF
Abstract.With the proliferation of voice interaction in intelligent cabins, voiceprint payment is becoming an important payment method in vehicular scenarios. However, deep learning-driven voice cloning technology has significantly lowered the barrier for generating forged speech, posing a serious threat to voiceprint authentication. The enclosed cabin environment, multi-microphone array layout, and real-time requirements make traditional anti-spoofing solutions difficult to migrate directly. This paper systematically analyzes the technological evolution of voice cloning attacks and the in-cabin threat model, constructs a multi-dimensional anti-spoofing evaluation benchmark covering detection performance, user experience, system overhead, and robustness, and proposes a four-layer defense strategy comprising input-layer liveness detection, feature-layer multimodal fusion, decision-layer risk grading, and application-layer transaction control. Experiments show that the proposed framework can reduce the attack success rate to 0.9%, while maintaining a false rejection rate of 0.7% for legitimate users and an authentication latency of 847 ms, providing a systematic reference for the security evaluation and protection of in-cabin voiceprint payment.
Keywords. Voice Cloning; Voiceprint Payment; Anti-Spoofing; Intelligent Cabin; Evaluation Benchmark; Layered Defense.
APA Citation Benyin Wu, Ruizhi Feng, Ziyi Wang, Yihong Qin (2026). Anti-Spoofing Evaluation Benchmark and Layered Defense Strategy for In-Cabin Voiceprint Payment under Voice Cloning Attacks. Scientific Journal of Technology, 8(9), 22-28. https://doi.org/10.54691/c57jbf30

References

  1. Todisco, M., Delgado, H., & Evans, N. W. D. (2016). A constant Q cepstral coefficients countermeasure for anti-spoofing in automatic speaker verification. In Interspeech 2016 (pp. 1428–1432). https: // doi. org/10.21437/Interspeech.2016-1131.
  2. Kinnunen, T., Delgado, H., Evans, N., et al. (2019). ASVspoof 2019: future horizons in spoofed and fake audio detection. In Interspeech 2019 (pp. 1003–1007). https://doi.org/10. 21437/ Interspeech. 2019-1431.
  3. Yamagishi, J., Wang, X., Todisco, M., et al. (2021). ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection. In ASVspoof 2021 Workshop. https://doi.org/10. 21437/ ASVSP OOF. 2021-1.
  4. Wang, Y., Deng, J., Xue, L., et al. (2023). VALL-E: neural codec language models for zero-shot text-to-speech. In ICLR 2023. https://doi.org/10.48550/arXiv.2301.02111.
  5. Cocharan, J., de Andrade, L. C., Junior, H. M., et al. (2022). YourTTS: towards zero-shot multi-speaker TTS and zero-shot voice conversion. In ICASSP 2022 (pp. 5637–5641). https://doi.org/10. 1109/ ICASSP43922.2022.9747161.
  6. Desplanques, B., Thienpondt, J., & Demuynck, K. (2020). ECAPA-TDNN: emphasized channel attention, propagation and aggregation in TDNN based speaker verification. In Interspeech 2020 (pp. 3830–3834). https://doi.org/10.21437/Interspeech.2020-2050.
  7. Tak, H., Patino, J., Todisco, M., et al. (2021). End-to-end anti-spoofing with RawNet2. In ICASSP 2021 (pp. 6369–6373). https://doi.org/10.1109/ICASSP39728.2021.9414770.
  8. Chen, S., Wang, C., Chen, Z., et al. (2023). Robust anti-spoofing for speaker verification with self-supervised pre-trained models. In ICASSP 2023 (pp. 1–5). https://doi.org/10. 1109/ ICASS P49357. 2023. 10096129.
  9. Zhang, X. Y., Li, T., & Jia, H. R. (2022). Research progress of voice anti-spoofing technology. Acta Automatica Sinica, 48(5), 1153–1172.
  10. Zheng, F., & Liu, B. (2021). Voiceprint recognition technology and its application in the financial field. Financial Computer of China, 29(8), 12–18.
  11. Cerence Inc. (2020, July 30). Cerence Pay: secure voice-powered payments in the car [EB/OL]. Retrieved June 15, 2024, from https://cerence.com.
  12. Baser, O., et al. (2024). SecureSpectra: safeguarding digital identity from deep fake threats via intelligent signatures. arXiv preprint arXiv:2407.00913. https://doi.org/ 10.48550/ arXiv. 2407. 00913.
  13. State Administration for Market Regulation. (2022). GB/T 7713.2—2022 Rules for Academic Paper Writing. Standards Press of China.