# Anti-spoofing and adversarial audio attacks

Area: [Speech and audio language models](https://mlsanity.com/speech/index.md). HTML: https://mlsanity.com/speech/anti-spoofing-and-adversarial-audio-attacks/

## 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).
- 67 of its 449 mapped papers (15%) cite “Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentation” (2022, arXiv 2202.12233).
- 7 new papers 2 Oct–19 Oct.

## Most cited here

- [ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection](https://mlsanity.com/paper/2109.00537/) (2021), cited by 100 papers here
- [Automatic speaker verification spoofing and deepfake detection using wav2vec 2.0 and data augmentation](https://mlsanity.com/paper/2202.12233/) (2022), cited by 67 papers here
- [Does Audio Deepfake Detection Generalize?](https://mlsanity.com/paper/2203.16263/) (2022), cited by 58 papers here
- [End-to-End Spectro-Temporal Graph Attention Networks for Speaker Verification Anti-Spoofing and Speech Deepfake Detection](https://mlsanity.com/paper/2107.12710/) (2021), cited by 47 papers here
- [MLAAD: The Multi-Language Audio Anti-Spoofing Dataset](https://mlsanity.com/paper/2401.09512/) (2024), cited by 32 papers here
- [WaveGuard: Understanding and Mitigating Audio Adversarial Examples](https://mlsanity.com/paper/2103.03344/) (2021), cited by 22 papers here
- [Audio Deepfake Detection with Self-Supervised WavLM and Multi-Fusion Attentive Classifier](https://mlsanity.com/paper/2312.08089/) (2023), cited by 21 papers here
- [The Codecfake Dataset and Countermeasures for the Universally Detection of Deepfake Audio](https://mlsanity.com/paper/2405.04880/) (2024), cited by 20 papers here
- [The PartialSpoof Database and Countermeasures for the Detection of Short Fake Speech Segments Embedded in an Utterance](https://mlsanity.com/paper/2204.05177/) (2022), cited by 19 papers here
- [AdvWave: Stealthy Adversarial Jailbreak Attack against Large Audio-Language Models](https://mlsanity.com/paper/2412.08608/) (2024), cited by 19 papers here

## New (2 Oct–19 Oct)

- [SENTRY: A Streaming Edge Network Trust Engine for Real-Time Audio Deepfake Detection](https://mlsanity.com/paper/2610.24468/) (2026-10-17)
- [VoxAnon: A balanced dataset for a fair evaluation of speech anonymization](https://mlsanity.com/paper/2610.13313/) (2026-10-09)
- [Backdooring Acoustic Foundation Models for Physically Realizable Triggers](https://mlsanity.com/paper/2610.09819/) (2026-10-07)
- [Breaking Adversarial Transferability in Fine-Tuned Speech Recognition](https://mlsanity.com/paper/2610.09109/) (2026-10-06)
- [Exploiting Acoustic and Content-Oriented Speaker Verification Attacks Against Multilingual Voice Anonymization](https://mlsanity.com/paper/2610.08107/) (2026-10-06)
- [Transferable Adversarial Robustness for Speech Foundation Models via Hierarchical Stabilization](https://mlsanity.com/paper/2610.05310/) (2026-10-04)
- [Task-Aware Joint Pruning and Distillation for Efficient Audio Deepfake Detection](https://mlsanity.com/paper/2610.05264/) (2026-10-04)