mlsanityData to 14 Oct 2026

Sequential Randomized Smoothing for Adversarially Robust Speech Recognition

arXiv 2112.03000 ↗First posted 5 Nov 2021cs.CL cs.AIcited by 13

Not on the map. Why?

Abstract (arXiv)

While Automatic Speech Recognition has been shown to be vulnerable to adversarial attacks, defenses against these attacks are still lagging. Existing, naive defenses can be partially broken with an adaptive attack. In classification tasks, the Randomized Smoothing paradigm has been shown to be effective at defending models. However, it is difficult to apply this paradigm to ASR tasks, due to their complexity and the sequential nature of their outputs. Our paper overcomes some of these challenges by leveraging speech-specific tools like enhancement and ROVER voting to design an ASR model that is robust to perturbations. We apply adaptive versions of state-of-the-art attacks, such as the Imperceptible ASR attack, to our model, and show that our strongest defense is robust to all attacks that use inaudible noise, and can only be broken with very high distortion.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 32 of its 59 references that are in the map. First posted on arXiv 5 Nov 2021.

Builds on

32 of 59 references.

References · 32

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  3. 2013Intriguing properties of neural networkscited by 5,155
  4. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  5. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
  6. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  7. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
  8. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 744
  9. 2020Fast is better than free: Revisiting adversarial trainingcited by 727
  10. 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 678
  11. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 567
  12. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 546
20 more
  1. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 468
  2. 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
  3. 2018On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Modelscited by 328
  4. 2018Audio Adversarial Examples: Targeted Attacks on Speech-to-Textcited by 274
  5. 2019Adversarial Training and Robustness for Multiple Perturbationscited by 183
  6. 2017SEGAN: Speech Enhancement Generative Adversarial Networkcited by 166
  7. 2017Towards Robust Neural Networks via Random Self-ensemblecited by 159
  8. 2019Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognitioncited by 124
  9. 2018Adversarial Attacks Against Automatic Speech Recognition Systems via Psychoacoustic Hidingcited by 85
  10. 2017DolphinAtack: Inaudible Voice Commandscited by 69
  11. 2018CommanderSong: A Systematic Approach for Practical Adversarial Voice Recognitioncited by 66
  12. 2017Mitigating Evasion Attacks to Deep Neural Networks via Region-based Classificationcited by 56
  13. 2018Robust Audio Adversarial Example for a Physical Attackcited by 44
  14. 2019Hear "No Evil", See "Kenansville": Efficient and Transferable Black-Box Attacks on Speech Recognition and Voice Identification Systemscited by 38
  15. 2018Characterizing Audio Adversarial Examples Using Temporal Dependencycited by 36
  16. 2019Espresso: A Fast End-to-end Neural Speech Recognition Toolkitcited by 31
  17. 2019Adversarial Music: Real World Audio Adversary Against Wake-word Detection Systemcited by 20
  18. 2021Adversarial Attacks and Defenses for Speech Recognition Systemscited by 20
  19. 2019Perceptual Based Adversarial Audio Attackscited by 13
  20. 2018Training Augmentation with Adversarial Examples for Robust Speech Recognitioncited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 3; 2023: 2; 2024: 1; 2025: 1; 2026: 6.

13 papers.

Sort:

By area:

  1. 2022Recent improvements of ASR models in the face of adversarial attackscited by 13
  2. 2022There is more than one kind of robustness: Fooling Whisper with adversarial examplescited by 11
  3. 2024Certification of Speaker Recognition Models to Additive Perturbationscited by 6
  4. 2022Watch What You Pretrain For: Targeted, Transferable Adversarial Examples on Self-Supervised Speech Recognition modelscited by 2
  5. 2026Evaluating randomized smoothing as a defense against adversarial attacks in trajectory predictioncited by 1
  6. 2026Codec-Robust Attacks on Audio LLMscited by 1
  7. 2023General Lipschitz: Certified Robustness Against Resolvable Semantic Transformations via Transformation-Dependent Randomized Smoothingcited by 0
  8. 2023STR-Cert: Robustness Certification for Deep Text Recognition on Deep Learning Pipelines and Vision Transformerscited by 0
  9. 2025Are Deep Speech Denoising Models Robust to Adversarial Noise?cited by 0
  10. 2026Representation Matters in Randomized Smoothing for Audio Classificationcited by 0
  11. 2026Beyond Waveform Robustness: Robust Feature-Vocoder Adversarial Attacks on Automatic Speech Recognitioncited by 0
  12. 2026What Was That Again? Certified Robustness for Automatic Speech Recognitioncited by 0
1 more
  1. 2026Psychoacoustically Aligned Latent Smoothing for Adversarial Robustness of Full-Duplex Speech-to-Speech Dialogue Modelscited by 0