# Towards Understanding and Mitigating Audio Adversarial Examples for Speaker Recognition

arXiv: https://arxiv.org/abs/2206.03393 · HTML: https://mlsanity.com/paper/2206.03393/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 58 of its 120 references that are in the map.
- First posted on arXiv 7 Jun 2022.

## Builds on (most cited first, 30 of 58)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples](https://mlsanity.com/paper/1802.00420/) (2018)
- [VoxCeleb: a large-scale speaker identification dataset](https://mlsanity.com/paper/1706.08612/) (2017)
- [LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech](https://mlsanity.com/paper/1904.02882/) (2019)
- [On Adaptive Attacks to Adversarial Example Defenses](https://mlsanity.com/paper/2002.08347/) (2020)
- [Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methods](https://mlsanity.com/paper/1705.07263/) (2017)
- [Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks](https://mlsanity.com/paper/1704.01155/) (2017)
- [Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Models](https://mlsanity.com/paper/1712.04248/) (2017)
- [Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey](https://mlsanity.com/paper/1801.00553/) (2018)
- [Tutorial on Variational Autoencoders](https://mlsanity.com/paper/1606.05908/) (2016)
- [Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Models](https://mlsanity.com/paper/1805.06605/) (2018)
- [Audio Adversarial Examples: Targeted Attacks on Speech-to-Text](https://mlsanity.com/paper/1801.01944/) (2018)
- [MagNet: a Two-Pronged Defense against Adversarial Examples](https://mlsanity.com/paper/1705.09064/) (2017)
- [Adversarial Robustness Toolbox v1.0.0](https://mlsanity.com/paper/1807.01069/) (2018)
- [Data Augmentation Can Improve Robustness](https://mlsanity.com/paper/2111.05328/) (2021)
- [Efficient Decision-based Black-box Adversarial Attacks on Face Recognition](https://mlsanity.com/paper/1904.04433/) (2019)
- [Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognition](https://mlsanity.com/paper/1903.10346/) (2019)
- [NATTACK: Learning the Distributions of Adversarial Examples for an Improved Black-Box Attack on Deep Neural Networks](https://mlsanity.com/paper/1905.00441/) (2019)
- [Deep Learning for Audio Signal Processing](https://mlsanity.com/paper/1905.00078/) (2019)
- [Adversarial Attacks Against Automatic Speech Recognition Systems via Psychoacoustic Hiding](https://mlsanity.com/paper/1808.05665/) (2018)
- [DolphinAtack: Inaudible Voice Commands](https://mlsanity.com/paper/1708.09537/) (2017)
- [Who is Real Bob? Adversarial Attacks on Speaker Recognition Systems](https://mlsanity.com/paper/1911.01840/) (2019)
- [CommanderSong: A Systematic Approach for Practical Adversarial Voice Recognition](https://mlsanity.com/paper/1801.08535/) (2018)
- [Deep Speaker: an End-to-End Neural Speaker Embedding System](https://mlsanity.com/paper/1705.02304/) (2017)
- [On the Suitability of Lp-norms for Creating and Preventing Adversarial Examples](https://mlsanity.com/paper/1802.09653/) (2018)
- [SoK: The Faults in our ASRs: An Overview of Attacks against Automatic Speech Recognition and Speaker Identification Systems](https://mlsanity.com/paper/2007.06622/) (2020)

## Built on by (most cited first, 23 of 23)

- [Stealthy Backdoor Attack for Code Models](https://mlsanity.com/paper/2301.02496/) (2023)
- [Defending against Adversarial Audio via Diffusion Model](https://mlsanity.com/paper/2303.01507/) (2023)
- [AudioJailbreak: Jailbreak Attacks against End-to-End Large Audio-Language Models](https://mlsanity.com/paper/2505.14103/) (2025)
- [SLMIA-SR: Speaker-Level Membership Inference Attacks against Speaker Recognition Systems](https://mlsanity.com/paper/2309.07983/) (2023)
- [I Can Hear You: Selective Robust Training for Deepfake Audio Detection](https://mlsanity.com/paper/2411.00121/) (2024)
- [QVIP: An ILP-based Formal Verification Approach for Quantized Neural Networks](https://mlsanity.com/paper/2212.11138/) (2022)
- [QEBVerif: Quantization Error Bound Verification of Neural Networks](https://mlsanity.com/paper/2212.02781/) (2022)
- [The defender's perspective on automatic speaker verification: An overview](https://mlsanity.com/paper/2305.12804/) (2023)
- [QFA2SR: Query-Free Adversarial Transfer Attacks to Speaker Recognition Systems](https://mlsanity.com/paper/2305.14097/) (2023)
- [`From Prompt to Perturbation': An Adaptive Framework for Voice-Based Jailbreaks on Audio LLMs](https://mlsanity.com/paper/2502.00735/) (2025)
- [SongBsAb: A Dual Prevention Approach against Singing Voice Conversion based Illegal Song Covers](https://mlsanity.com/paper/2401.17133/) (2024)
- [Towards Sample-specific Backdoor Attack with Clean Labels via Attribute Trigger](https://mlsanity.com/paper/2312.04584/) (2023)
- [Detecting and Defending Against Adversarial Attacks on Automatic Speech Recognition via Diffusion Models](https://mlsanity.com/paper/2409.07936/) (2024)
- [De-AntiFake: Rethinking the Protective Perturbations Against Voice Cloning Attacks](https://mlsanity.com/paper/2507.02606/) (2025)
- [Scores Know Bobs Voice: Speaker Impersonation Attack](https://mlsanity.com/paper/2603.02781/) (2026)
- [Unraveling Adversarial Examples against Speaker Identification -- Techniques for Attack Detection and Victim Model Classification](https://mlsanity.com/paper/2402.19355/) (2024)
- [Adversarially Robust Deepfake Detection via Adversarial Feature Similarity Learning](https://mlsanity.com/paper/2403.08806/) (2024)
- [Training Verification-Friendly Neural Networks via Neuron Behavior Consistency](https://mlsanity.com/paper/2412.13229/) (2024)
- [Investigating Vulnerabilities and Defenses Against Audio-Visual Attacks: A Comprehensive Survey Emphasizing Multimodal Models](https://mlsanity.com/paper/2506.11521/) (2025)
- [An Automata-Theoretic Approach to Synthesizing Binarized Neural Networks](https://mlsanity.com/paper/2307.15907/) (2023)
- [Scalable Ensemble-based Detection Method against Adversarial Attacks for speaker verification](https://mlsanity.com/paper/2312.08622/) (2023)
- [On the Generation and Removal of Speaker Adversarial Perturbation for Voice-Privacy Protection](https://mlsanity.com/paper/2412.09195/) (2024)
- [Are Deep Speech Denoising Models Robust to Adversarial Noise?](https://mlsanity.com/paper/2503.11627/) (2025)

## Abstract (arXiv)

Speaker recognition systems (SRSs) have recently been shown to be vulnerable to adversarial attacks, raising significant security concerns. In this work, we systematically investigate transformation and adversarial training based defenses for securing SRSs. According to the characteristic of SRSs, we present 22 diverse transformations and thoroughly evaluate them using 7 recent promising adversarial attacks (4 white-box and 3 black-box) on speaker recognition. With careful regard for best practices in defense evaluations, we analyze the strength of transformations to withstand adaptive attacks. We also evaluate and understand their effectiveness against adaptive attacks when combined with adversarial training. Our study provides lots of useful insights and findings, many of them are new or inconsistent with the conclusions in the image and speech recognition domains, e.g., variable and constant bit rate speech compressions have different performance, and some non-differentiable transformations remain effective against current promising evasion techniques which often work well in the image domain. We demonstrate that the proposed novel feature-level transformation combined with adversarial training is rather effective compared to the sole adversarial training in a complete white-box setting, e.g., increasing the accuracy by 13.62% and attack cost by two orders of magnitude, while other transformations do not necessarily improve the overall defense capability. This work sheds further light on the research directions in this field. We also release our evaluation platform SPEAKERGUARD to foster further research.