mlsanityData to 14 Oct 2026

The defender's perspective on automatic speaker verification: An overview

arXiv 2305.12804 ↗First posted 22 May 2023cs.SD cs.LG eess.AScited by 9

Not on the map. Why?

Abstract (arXiv)

Automatic speaker verification (ASV) plays a critical role in security-sensitive environments. Regrettably, the reliability of ASV has been undermined by the emergence of spoofing attacks, such as replay and synthetic speech, as well as adversarial attacks and the relatively new partially fake speech. While there are several review papers that cover replay and synthetic speech, and adversarial attacks, there is a notable gap in a comprehensive review that addresses defense against adversarial attacks and the recently emerged partially fake speech. Thus, the aim of this paper is to provide a thorough and systematic overview of the defense methods used against these types of attacks.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 33 of its 48 references that are in the map. First posted on arXiv 22 May 2023.

Builds on

33 of 48 references.

References · 33

  1. 2013Intriguing properties of neural networkscited by 5,155
  2. 2013Auto-Encoding Variational Bayescited by 4,053
  3. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  4. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,657
  5. 2021XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scalecited by 601
  6. 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
  7. 2019ASVspoof 2019: Future Horizons in Spoofed and Fake Audio Detectioncited by 178
  8. 2021ASVspoof 2021: accelerating progress in spoofed and deepfake speech detectioncited by 161
  9. 2022ADD 2022: the First Audio Deep Synthesis Detection Challengecited by 96
  10. 2019Who is Real Bob? Adversarial Attacks on Speaker Recognition Systemscited by 67
  11. 2022The PartialSpoof Database and Countermeasures for the Detection of Short Fake Speech Segments Embedded in an Utterancecited by 47
  12. 2020SoK: The Faults in our ASRs: An Overview of Attacks against Automatic Speech Recognition and Speaker Identification Systemscited by 46
21 more
  1. 2021Half-Truth: A Partially Fake Audio Detection Datasetcited by 44
  2. 2018Fooling End-to-end Speaker Verification by Adversarial Examplescited by 39
  3. 2019SirenAttack: Generating Adversarial Audio for End-to-End Acoustic Systemscited by 34
  4. 2021An Initial Investigation for Detecting Partially Spoofed Audiocited by 27
  5. 2019Adversarial Attacks on Spoofing Countermeasures of automatic speaker verificationcited by 23
  6. 2019Adversarial Attacks on GMM i-vector based Speaker Verification Systemscited by 23
  7. 2022Towards Understanding and Mitigating Audio Adversarial Examples for Speaker Recognitioncited by 23
  8. 2020Adversarial Attack and Defense Strategies for Deep Speaker Recognition Systemscited by 21
  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. 2021Improving the Adversarial Robustness for Speaker Verification by Self-Supervised Learningcited by 16
  12. 2021Multi-Task Learning in Utterance-Level and Segmental-Level Spoof Detectioncited by 16
  13. 2022Waveform Boundary Detection for Partially Spoofed Audiocited by 15
  14. 2020Investigating Robustness of Adversarial Samples Detection for Automatic Speaker Verificationcited by 14
  15. 2022Partially Fake Audio Detection by Self-attention-based Fake Span Discoverycited by 14
  16. 2021Voting for the right answer: Adversarial defense for speaker verificationcited by 12
  17. 2021Adversarial Sample Detection for Speaker Verification by Neural Vocoderscited by 8
  18. 2022AdvEst: Adversarial Perturbation Estimation to Classify and Detect Adversarial Attacks against Speaker Identificationcited by 4
  19. 2021Representation Learning to Classify and Detect Adversarial Attacks against Speaker and Speech Recognition Systemscited by 3
  20. 2022LMD: A Learnable Mask Network to Detect Adversarial Examples for Speaker Verificationcited by 2
  21. 2022Synthetic Voice Detection and Audio Splicing Detection using SE-Res2Net-Conformer Architecturecited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 4; 2025: 3; 2026: 1.

9 papers.

  1. 2024Temporal-Channel Modeling in Multi-head Self-Attention for Synthetic Speech Detectioncited by 25
  2. 2024DFADD: The Diffusion and Flow-Matching Based Audio Deepfake Datasetcited by 20
  3. 2024Coarse-to-Fine Proposal Refinement Framework for Audio Temporal Forgery Detection and Localizationcited by 9
  4. 2023Scalable Ensemble-based Detection Method against Adversarial Attacks for speaker verificationcited by 0
  5. 2024On the Generation and Removal of Speaker Adversarial Perturbation for Voice-Privacy Protectioncited by 0
  6. 2025Towards Generalized Source Tracing for Codec-Based Deepfake Speechcited by 0
  7. 20253-Tracer: A Tri-level Temporal-Aware Framework for Audio Forgery Detection and Localizationcited by 0
  8. 2025Degrading Voice: A Comprehensive Overview of Robust Voice Conversion Through Input Manipulationcited by 0
  9. 2026Adaptive Compression and Targeted Perturbation: A Unified Framework for Generalized Audio Deepfake Detectioncited by 0