mlsanityData to 14 Oct 2026

Real-Time Neural Voice Camouflage

arXiv 2112.07076 ↗First posted 14 Dec 2021cs.SD cs.LG eess.AScited by 6

Not on the map. Why?

Abstract (arXiv)

Automatic speech recognition systems have created exciting possibilities for applications, however they also enable opportunities for systematic eavesdropping. We propose a method to camouflage a person's voice over-the-air from these systems without inconveniencing the conversation between people in the room. Standard adversarial attacks are not effective in real-time streaming situations because the characteristics of the signal will have changed by the time the attack is executed. We introduce predictive attacks, which achieve real-time performance by forecasting the attack that will be the most effective in the future. Under real-time constraints, our method jams the established speech recognition system DeepSpeech 3.9x more than baselines as measured through word error rate, and 6.6x more as measured through character error rate. We furthermore demonstrate our approach is practically effective in realistic environments over physical distances.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 33 of its 45 references that are in the map. First posted on arXiv 14 Dec 2021.

Builds on

33 of 45 references.

References · 33

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  4. 2013Intriguing properties of neural networkscited by 5,155
  5. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  6. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  7. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  8. 2016Adversarial examples in the physical worldcited by 1,769
  9. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
  10. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  11. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  12. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
21 more
  1. 2018Robustness May Be at Odds with Accuracycited by 880
  2. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 776
  3. 2020Fast is better than free: Revisiting adversarial trainingcited by 727
  4. 2015Deep Speech 2: End-to-End Speech Recognition in English and Mandarincited by 451
  5. 2019Unlabeled Data Improves Adversarial Robustnesscited by 416
  6. 2014Deep Speech: Scaling up end-to-end speech recognitioncited by 354
  7. 2018Audio Adversarial Examples: Targeted Attacks on Speech-to-Textcited by 274
  8. 2018Generating Adversarial Examples with Adversarial Networkscited by 258
  9. 2019Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognitioncited by 124
  10. 2018Adversarial Attacks Against Automatic Speech Recognition Systems via Psychoacoustic Hidingcited by 85
  11. 2019Metric Learning for Adversarial Robustnesscited by 77
  12. 2021Adversarial Attacks are Reversible with Natural Supervisioncited by 47
  13. 2018Robust Audio Adversarial Example for a Physical Attackcited by 44
  14. 2019Adversarial Music: Real World Audio Adversary Against Wake-word Detection Systemcited by 20
  15. 2021Adversarial Attacks and Defenses for Speech Recognition Systemscited by 20
  16. 2019Adversarial Generation of Time-Frequency Features with application in audio synthesiscited by 13
  17. 2021Adversarial Robustness of Streaming Algorithms through Importance Samplingcited by 13
  18. 2019Real-Time Adversarial Attackscited by 11
  19. 2021Exploring Targeted Universal Adversarial Perturbations to End-to-end ASR Modelscited by 10
  20. 2020Listening to Sounds of Silence for Speech Denoisingcited by 9
  21. 2021Adversarial Auto-Encoding for Packet Loss Concealmentcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 1; 2024: 1; 2025: 2; 2026: 1.

6 papers.

  1. 2023Adversarial Examples in the Physical World: A Surveycited by 10
  2. 2024DynamicPAE: Generating Scene-Aware Physical Adversarial Examples in Real-Timecited by 4
  3. 2025Whispering Under the Eaves: Protecting User Privacy Against Commercial and LLM-powered Automatic Speech Recognition Systemscited by 2
  4. 2022Universal Fourier Attack for Time Seriescited by 1
  5. 2025AegisRF: Adversarial Perturbations Guided with Sensitivity for Protecting Intellectual Property of Neural Radiance Fieldscited by 0
  6. 2026Hearing the Unspoken: Language Model Priors for Acoustic Adversarial Attackscited by 0