mlsanityData to 19 Oct 2026

Anti-spoofing and adversarial audio attacks

449 papers0 this weekHigh confidence in this grouping: the papers form one clear topicHigh confidence in this grouping: the papers form one clear topic · About

Keywords: attacks, audio, adversarial, detection, speech

Key facts. Anti-spoofing and adversarial audio attacks: 449 papers on arXiv since 2021 (data through 19 Oct 2026). 100 of its 449 mapped papers (22%) cite “ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection” (2021, arXiv 2109.00537). 7 new papers 2 Oct–19 Oct.

What’s new

2 Oct – 19 Oct 2026

7 new papers, 2 Oct – 19 Oct; 0 this week.

  1. Earlier · 7
  2. SENTRY: A Streaming Edge Network Trust Engine for Real-Time Audio Deepfake Detection
  3. VoxAnon: A balanced dataset for a fair evaluation of speech anonymization
  4. Backdooring Acoustic Foundation Models for Physically Realizable Triggers
  5. Breaking Adversarial Transferability in Fine-Tuned Speech Recognition
  6. Exploiting Acoustic and Content-Oriented Speaker Verification Attacks Against Multilingual Voice Anonymization
  7. Transferable Adversarial Robustness for Speech Foundation Models via Hierarchical Stabilization
  8. Task-Aware Joint Pruning and Distillation for Efficient Audio Deepfake Detection

Foundations

Most cited by papers here

  1. ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection2021cited by 100 here
  2. Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentation2022cited by 67 here
  3. Does Audio Deepfake Detection Generalize?2022cited by 58 here
  4. End-to-End Spectro-Temporal Graph Attention Networks for Speaker Verification Anti-Spoofing and Speech Deepfake Detection2021cited by 47 here
  5. MLAAD: The Multi-Language Audio Anti-Spoofing Dataset2024cited by 32 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2021Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speechcited by 44 here
  2. 2021A Survey on Neural Speech Synthesiscited by 17 here
  3. 2021YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyonecited by 30 here
  4. 2023Neural Codec Language Models are Zero-Shot Text to Speech Synthesizerscited by 32 here
  5. 2024F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matchingcited by 22 here
19 more it builds on, not in this chain
  1. 2021WaveGuard: Understanding and Mitigating Audio Adversarial Examplescited by 22 here
  2. 2021SoundStream: An End-to-End Neural Audio Codeccited by 19 here
  3. 2021End-to-End Spectro-Temporal Graph Attention Networks for Speaker Verification Anti-Spoofing and Speech Deepfake Detectioncited by 47 here
  4. 2021ASVspoof 2021: accelerating progress in spoofed and deepfake speech detectioncited by 100 here
  5. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 87 here
  6. 2021XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scalecited by 39 here
  7. 2022Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentationcited by 67 here
  8. 2022Does Audio Deepfake Detection Generalize?cited by 58 here
  9. 2022The PartialSpoof Database and Countermeasures for the Detection of Short Fake Speech Segments Embedded in an Utterancecited by 19 here
  10. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 95 here
  11. 2023SALMONN: Towards Generic Hearing Abilities for Large Language Modelscited by 19 here
  12. 2023Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Modelscited by 20 here
  13. 2023Audio Deepfake Detection with Self-Supervised WavLM and Multi-Fusion Attentive Classifiercited by 21 here
  14. 2024MLAAD: The Multi-Language Audio Anti-Spoofing Datasetcited by 32 here
  15. 2024The Codecfake Dataset and Countermeasures for the Universally Detection of Deepfake Audiocited by 20 here
  16. 2024XTTS: a Massively Multilingual Zero-Shot Text-to-Speech Modelcited by 21 here
  17. 2024Qwen2-Audio Technical Reportcited by 20 here
  18. 2024SpoofCeleb: Speech Deepfake Detection and SASV In The Wildcited by 18 here
  19. 2024AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Modelscited by 19 here

The 24 most cited of 840.

Browse

30 of 449, ranked 6–35

  1. 6WaveGuard: Understanding and Mitigating Audio Adversarial Examples202122
  2. 7Audio Deepfake Detection with Self-Supervised WavLM and Multi-Fusion Attentive Classifier202321
  3. 8The Codecfake Dataset and Countermeasures for the Universally Detection of Deepfake Audio202420
  4. 9AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Models202419
  5. 10The PartialSpoof Database and Countermeasures for the Detection of Short Fake Speech Segments Embedded in an Utterance202219
  6. 11SpoofCeleb: Speech Deepfake Detection and SASV In The Wild202418
  7. 12Spoofed training data for speech spoofing countermeasure can be efficiently created using neural vocoders202216
  8. 13CodecFake: Enhancing Anti-Spoofing Models Against Deepfake Audios from Codec-Based Speech Synthesis Systems202415
  9. 14Improving the Adversarial Robustness for Speaker Verification by Self-Supervised Learning202115
  10. 15Multilingual and Multi-Accent Jailbreaking of Audio LLMs202513
All 30
  1. 16End-to-End Speech Recognition from Federated Acoustic Models202113
  2. 17Source Tracing of Audio Deepfake Systems202412
  3. 18Baseline Systems for the First Spoofing-Aware Speaker Verification Challenge: Score and Embedding Fusion202211
  4. 19Audio Jailbreak: An Open Comprehensive Benchmark for Jailbreaking Large Audio-Language Models202510
  5. 20JALMBench: Benchmarking Jailbreak Vulnerabilities in Audio Language Models202510
  6. 21Recent improvements of ASR models in the face of adversarial attacks202210
  7. 22Towards Understanding and Mitigating Audio Adversarial Examples for Speaker Recognition202210
  8. 23Adversarial Attacks and Defenses for Speech Recognition Systems202110
  9. 24ASVspoof 5: Design, Collection and Validation of Resources for Spoofing, Deepfake, and Adversarial Attack Detection Using Crowdsourced Speech20259
  10. 25Nes2Net: A Lightweight Nested Architecture for Foundation Model Driven Speech Anti-spoofing20259
  11. 26Mixture of Experts Fusion for Fake Audio Detection Using Frozen wav2vec 2.020249
  12. 27The defender's perspective on automatic speaker verification: An overview20239
  13. 28What to Remember: Self-Adaptive Continual Learning for Audio Deepfake Detection20239
  14. 29The DKU-OPPO System for the 2022 Spoofing-Aware Speaker Verification Challenge20229
  15. 30SAMO: Speaker Attractor Multi-Center One-Class Learning for Voice Anti-Spoofing20229
  16. 31Federated Acoustic Modeling For Automatic Speech Recognition20219
  17. 32Adversarial defense for automatic speaker verification by cascaded self-supervised learning models20219
  18. 33Attack on practical speaker verification system using universal adversarial perturbations20219
  19. 34Channel-wise Gated Res2Net: Towards Robust Detection of Synthetic Speech Attacks20219
  20. 35Jailbreak-AudioBench: In-Depth Evaluation and Analysis of Jailbreak Threats for Large Audio Language Models20258