mlsanityData to 7 Oct 2026

Voting for the right answer: Adversarial defense for speaker verification

arXiv 2106.07868 ↗First posted 15 Jun 2021cs.LG cs.CR cs.SDcited by 12

Not on the map. Why?

Abstract (arXiv)

Automatic speaker verification (ASV) is a well developed technology for biometric identification, and has been ubiquitous implemented in security-critic applications, such as banking and access control. However, previous works have shown that ASV is under the radar of adversarial attacks, which are very similar to their original counterparts from human's perception, yet will manipulate the ASV render wrong prediction. Due to the very late emergence of adversarial attacks for ASV, effective countermeasures against them are limited. Given that the security of ASV is of high priority, in this work, we propose the idea of "voting for the right answer" to prevent risky decisions of ASV in blind spot areas, by employing random sampling and voting. Experimental results show that our proposed method improves the robustness against both the limited-knowledge attackers by pulling the adversarial samples out of the blind spots, and the perfect-knowledge attackers by introducing randomness and increasing the attackers' budgets.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 29 of its 42 references that are in the map. First posted on arXiv 15 Jun 2021.

Builds on

29 of 42 references.

References · 29

  1. 2013Intriguing properties of neural networkscited by 5,114
  2. 2016Adversarial Machine Learning at Scalecited by 934
  3. 2018VoxCeleb2: Deep Speaker Recognitioncited by 862
  4. 2017VoxCeleb: a large-scale speaker identification datasetcited by 714
  5. 2020On Adaptive Attacks to Adversarial Example Defensescited by 547
  6. 2018Audio Adversarial Examples: Targeted Attacks on Speech-to-Textcited by 268
  7. 2019ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detectioncited by 173
  8. 2019Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognitioncited by 123
  9. 2020In defence of metric learning for speaker recognitioncited by 123
  10. 2018Attentive Statistics Pooling for Deep Speaker Embeddingcited by 108
  11. 2018Adversarial Attacks Against Automatic Speech Recognition Systems via Psychoacoustic Hidingcited by 83
  12. 2019Who is Real Bob? Adversarial Attacks on Speaker Recognition Systemscited by 66
17 more
  1. 2018CommanderSong: A Systematic Approach for Practical Adversarial Voice Recognitioncited by 63
  2. 2020Backdoor Attack against Speaker Verificationcited by 62
  3. 2018Robust Audio Adversarial Example for a Physical Attackcited by 42
  4. 2018Fooling End-to-end Speaker Verification by Adversarial Examplescited by 39
  5. 2020Real-time, Universal, and Robust Adversarial Attacks Against Speaker Recognition Systemscited by 26
  6. 2019Adversarial Attacks on Spoofing Countermeasures of automatic speaker verificationcited by 23
  7. 2019Adversarial Attacks on GMM i-vector based Speaker Verification Systemscited by 23
  8. 2020Defending Your Voice: Adversarial Attack on Voice Conversioncited by 23
  9. 2020Defense against adversarial attacks on spoofing countermeasures of ASVcited by 20
  10. 2020The Attacker's Perspective on Automatic Speaker Verification: An Overviewcited by 19
  11. 2020Characterizing Speech Adversarial Examples Using Self-Attention U-Net Enhancementcited by 18
  12. 2021Adversarial defense for automatic speaker verification by cascaded self-supervised learning modelscited by 16
  13. 2021Improving the Adversarial Robustness for Speaker Verification by Self-Supervised Learningcited by 16
  14. 2020Investigating Robustness of Adversarial Samples Detection for Automatic Speaker Verificationcited by 14
  15. 2020Inaudible Adversarial Perturbations for Targeted Attack in Speaker Recognitioncited by 13
  16. 2020Defense for Black-box Attacks on Anti-spoofing Models by Self-Supervised Learningcited by 12
  17. 2017Deep Speaker Feature Learning for Text-independent Speaker Verificationcited by 6

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 8; 2023: 2.

12 papers.

  1. 2022Towards Understanding and Mitigating Audio Adversarial Examples for Speaker Recognitioncited by 22
  2. 2022Partially Fake Audio Detection by Self-attention-based Fake Span Discoverycited by 14
  3. 2021Adversarial Sample Detection for Speaker Verification by Neural Vocoderscited by 8
  4. 2023The defender's perspective on automatic speaker verification: An overviewcited by 8
  5. 2021Characterizing the adversarial vulnerability of speech self-supervised learningcited by 5
  6. 2022On the Detection of Adaptive Adversarial Attacks in Speaker Verification Systemscited by 3
  7. 2022Push-Pull: Characterizing the Adversarial Robustness for Audio-Visual Active Speaker Detectioncited by 3
  8. 2022Spoofing-Aware Speaker Verification by Multi-Level Fusioncited by 2
  9. 2022Adversarial Speaker Distillation for Countermeasure Model on Automatic Speaker Verificationcited by 2
  10. 2022LMD: A Learnable Mask Network to Detect Adversarial Examples for Speaker Verificationcited by 2
  11. 2022Tackling Spoofing-Aware Speaker Verification with Multi-Model Fusioncited by 1
  12. 2023Scalable Ensemble-based Detection Method against Adversarial Attacks for speaker verificationcited by 0